Intriguing properties of neural networks
arXiv:1312.6199
Abstract
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they succeed, it also causes them to learn uninterpretable solutions that could have counter-intuitive properties. In this paper we report two such properties. First, we find that there is no distinction between individual high level units and random linear combinations of high level units, according to various methods of unit analysis. It suggests that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks. Second, we find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extend. We can cause the network to misclassify an image by applying a certain imperceptible perturbation, which is found by maximizing the network's prediction error. In addition, the specific nature of these perturbations is not a random artifact of learning: the same perturbation can cause a different network, that was trained on a different subset of the dataset, to misclassify the same input.
References in corpus (3)
Cited by in corpus (700)
- Explaining and Harnessing Adversarial Examples
- Deep learning with convolutional neural networks for EEG decoding and visualization
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Diffusion Models Beat GANs on Image Synthesis
- Shortcut Learning in Deep Neural Networks
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Understanding Neural Networks Through Deep Visualization
- Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- End-to-end Optimized Image Compression
- A trans-disciplinary review of deep learning research for water resources scientists
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Recent Advances in Open Set Recognition: A Survey
- Deep Neural Networks and Tabular Data: A Survey
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Image Quality Assessment: Unifying Structure and Texture Similarity
- Robust Real-World Image Super-Resolution against Adversarial Attacks
- Theoretically Principled Trade-off between Robustness and Accuracy
- Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
- Applications of Deep Learning and Reinforcement Learning to Biological Data
- On instabilities of deep learning in image reconstruction - Does AI come at a cost?
- Blended Diffusion for Text-driven Editing of Natural Images
- Understanding Deep Convolutional Networks
- Synthesizing Robust Adversarial Examples
- Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Understanding Neural Networks through Representation Erasure
- Adversarial Personalized Ranking for Recommendation
- Artificial neural networks for neuroscientists: A primer
- Deep Text Classification Can be Fooled
- Understanding the Role of Individual Units in a Deep Neural Network
- Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
- Optimization Problems for Machine Learning: A Survey
- Generalizing Across Domains via Cross-Gradient Training
- Black-box Adversarial Attacks with Limited Queries and Information
- Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
- Adversarial Attack and Defense on Graph Data: A Survey
- DLFuzz: Differential Fuzzing Testing of Deep Learning Systems
- A Survey of End-to-End Driving: Architectures and Training Methods
- CNN Based Adversarial Embedding with Minimum Alteration for Image Steganography
- AdvHat: Real-world adversarial attack on ArcFace Face ID system
- Pathologies of Neural Models Make Interpretations Difficult
- X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
- Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
- Neural Trojans
- Adversarial Examples: Opportunities and Challenges
- Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
- Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks
- Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
- A Note on the Inception Score
- Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
- Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
- Learning to Compare Image Patches via Convolutional Neural Networks
- Stochastic Activation Pruning for Robust Adversarial Defense
- Measuring the tendency of CNNs to Learn Surface Statistical Regularities
- Evaluating and Improving Adversarial Robustness of Machine Learning-Based Network Intrusion Detectors
- Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
- Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
- Robust Audio Adversarial Example for a Physical Attack
- Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
- Towards Crafting Text Adversarial Samples
- Adversarial Attack on Graph Structured Data
- Quantum noise protects quantum classifiers against adversaries
- Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data
- AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
- SpaText: Spatio-Textual Representation for Controllable Image Generation
- Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
- Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
- Convolutional neural networks: a magic bullet for gravitational-wave detection?
- Smart Home Personal Assistants: A Security and Privacy Review
- Examining the Impact of Blur on Recognition by Convolutional Networks
- Adversarial Attacks on Deep Neural Networks for Time Series Classification
- advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
- A new approach to observational cosmology using the scattering transform
- PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy
- MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
- Training robust neural networks using Lipschitz bounds
- Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
- Trustworthy AI and Robotics and the Implications for the AEC Industry: A Systematic Literature Review and Future Potentials
- How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
- Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection
- Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming
- Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
- Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors
- Adversarial examples from computational constraints
- Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
- Delving into adversarial attacks on deep policies
- Poison Ink: Robust and Invisible Backdoor Attack
- Towards Proving the Adversarial Robustness of Deep Neural Networks
- Learning to Protect Communications with Adversarial Neural Cryptography
- Solving Electrical Impedance Tomography with Deep Learning
- RobustBench: a standardized adversarial robustness benchmark
- Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
- Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
- Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
- Are All Layers Created Equal?
- Going in circles is the way forward: the role of recurrence in visual inference
- Fast Feature Fool: A data independent approach to universal adversarial perturbations
- Fixed Point Strategies in Data Science
- Benchmarking Adversarial Patch Against Aerial Detection
- Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
- Machine learning with neural networks
- Deep Convolutional Networks as shallow Gaussian Processes
- Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
- Bayesian deep learning for error estimation in the analysis of anomalous diffusion
- Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
- Adversarial Attacks Against Deep Generative Models on Data: A Survey
- UPSET and ANGRI : Breaking High Performance Image Classifiers
- Verification for Machine Learning, Autonomy, and Neural Networks Survey
- Universal adversarial perturbations
- It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations
- Unsolved Problems in ML Safety
- Traffic Sign Detection under Challenging Conditions: A Deeper Look Into Performance Variations and Spectral Characteristics
- Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
- Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
- Revisiting the Importance of Individual Units in CNNs via Ablation
- Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
- Towards Adversarial Malware Detection: Lessons Learned from PDF-based Attacks
- AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
- Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Quality
- Real Time Image Saliency for Black Box Classifiers
- Adversarial Samples on Android Malware Detection Systems for IoT Systems
- Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction
- Graph Neural Networks with Continual Learning for Fake News Detection from Social Media
- Towards quantum enhanced adversarial robustness in machine learning
- Scattering Networks for Hybrid Representation Learning
- PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition
- Analyzing Human-Human Interactions: A Survey
- Robust Adversarial Perturbation on Deep Proposal-based Models
- Semantic Robustness of Models of Source Code
- Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks
- Adversarial Robustness May Be at Odds With Simplicity
- Deep Convolutional Neural Networks in the Face of Caricature: Identity and Image Revealed
- PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations
- A Counter-Forensic Method for CNN-Based Camera Model Identification
- OpenAttack: An Open-source Textual Adversarial Attack Toolkit
- Facial Attributes: Accuracy and Adversarial Robustness
- Unrestricted Adversarial Examples
- Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations
- Sensitivity Analysis of Deep Neural Networks
- Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes
- Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms
- Synesthesia: Detecting Screen Content via Remote Acoustic Side Channels
- Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
- Fast Facial Landmark Detection and Applications: A Survey
- Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
- FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
- 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection
- Hardware Trojan Attacks on Neural Networks
- How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
- Partial success in closing the gap between human and machine vision
- How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks
- Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
- Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
- Can Adversarial Weight Perturbations Inject Neural Backdoors?
- Maximal Jacobian-based Saliency Map Attack
- Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Study
- DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
- Analysis and Optimization of Convolutional Neural Network Architectures
- Machine Learning in NextG Networks via Generative Adversarial Networks
- Characterizing and evaluating adversarial examples for Offline Handwritten Signature Verification
- A Survey of Adversarial Learning on Graphs
- Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
- Detection of Face Recognition Adversarial Attacks
- Are Accuracy and Robustness Correlated?
- Discretization based Solutions for Secure Machine Learning against Adversarial Attacks
- Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification
- A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations
- Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
- A Survey of Game Theoretic Approaches for Adversarial Machine Learning in Cybersecurity Tasks
- Gotta CAPTCHA 'Em All: A Survey of Twenty years of the Human-or-Computer Dilemma
- Training individually fair ML models with Sensitive Subspace Robustness
- Boosting Adversarial Attacks with Momentum
- Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting
- Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
- Noise Flooding for Detecting Audio Adversarial Examples Against Automatic Speech Recognition
- CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World
- A Survey on State-of-the-art Deep Learning Applications and Challenges
- Robust in Practice: Adversarial Attacks on Quantum Machine Learning
- VisualBackProp: efficient visualization of CNNs
- Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
- Neural networks in pulsed dipolar spectroscopy: a practical guide
- Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
- Adversarial Attacks on Time-Series Intrusion Detection for Industrial Control Systems
- Defending against Adversarial Images using Basis Functions Transformations
- Detection of Gravitational Waves Using Bayesian Neural Networks
- Challenges in Building Intelligent Open-domain Dialog Systems
- Adversarial Attacks and Defenses for Semantic Communication in Vehicular Metaverses
- Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning
- Backdoors in Neural Models of Source Code
- Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
- Defending Against Universal Attacks Through Selective Feature Regeneration
- VC Classes are Adversarially Robustly Learnable, but Only Improperly
- Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
- Why is the Mahalanobis Distance Effective for Anomaly Detection?
- Deep Weighted Averaging Classifiers
- Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions
- Weighted-Sampling Audio Adversarial Example Attack
- Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval
- A deep architecture for unified aesthetic prediction
- Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
- Adversarial Patch Attacks on Monocular Depth Estimation Networks
- On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems
- Interpretable neural networks based on continuous-valued logic and multicriteria decision operators
- Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
- The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing
- On the Geometry of Adversarial Examples
- Biometric Backdoors: A Poisoning Attack Against Unsupervised Template Updating
- Topological Persistence Machine of Phase Transitions
- Adversarially Robust Neural Architectures
- Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
- The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning
- Re-evaluating Evaluation
- Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
- Generation & Evaluation of Adversarial Examples for Malware Obfuscation
- Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
- Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
- PAD: Towards Principled Adversarial Malware Detection Against Evasion Attacks
- PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
- Quality Resilient Deep Neural Networks
- Hybrid Channel Based Pedestrian Detection
- Pixle: a fast and effective black-box attack based on rearranging pixels
- Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
- Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
- Protecting Voice Controlled Systems Using Sound Source Identification Based on Acoustic Cues
- Quantifying Perceptual Distortion of Adversarial Examples
- One-Trial Correction of Legacy AI Systems and Stochastic Separation Theorems
- Security for Machine Learning-based Systems: Attacks and Challenges during Training and Inference
- White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks
- Ethical Considerations and Statistical Analysis of Industry Involvement in Machine Learning Research
- A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification
- Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
- Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
- Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
- Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition
- When and How to Fool Explainable Models (and Humans) with Adversarial Examples
- Using Videos to Evaluate Image Model Robustness
- Software Testing for Machine Learning
- ReachNN: Reachability Analysis of Neural-Network Controlled Systems
- Adversarial Robustness via Fisher-Rao Regularization
- Interpretability Beyond Classification Output: Semantic Bottleneck Networks
- The Future of Misinformation Detection: New Perspectives and Trends
- Increasing the Confidence of Deep Neural Networks by Coverage Analysis
- BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
- Deep reinforcement learning in World-Earth system models to discover sustainable management strategies
- Interpreting CNNs via Decision Trees
- Learning Security Classifiers with Verified Global Robustness Properties
- Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
- Assaying Out-Of-Distribution Generalization in Transfer Learning
- Exactly Computing the Local Lipschitz Constant of ReLU Networks
- To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout
- Gradient-free activation maximization for identifying effective stimuli
- Task dependent Deep LDA pruning of neural networks
- Query-Efficient Black-box Adversarial Examples (superceded)
- Adversarial Attacks on Machine Learning Systems for High-Frequency Trading
- Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning
- Multimodal neural networks better explain multivoxel patterns in the hippocampus
- Sensitivity analysis of Wasserstein distributionally robust optimization problems
- Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
- Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
- TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks
- Towards Frequency-Based Explanation for Robust CNN
- Perfect density models cannot guarantee anomaly detection
- Interpretable Convolutional Neural Networks
- Uncertainty Injection: A Deep Learning Method for Robust Optimization
- A Unified Gradient Regularization Family for Adversarial Examples
- Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
- ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification System
- Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
- The Emergence of Canalization and Evolvability in an Open-Ended, Interactive Evolutionary System
- RobustECD: Enhancement of Network Structure for Robust Community Detection
- The SP theory of intelligence: distinctive features and advantages
- Improving the Adversarial Robustness of NLP Models by Information Bottleneck
- Constrained Learning with Non-Convex Losses
- Towards Visual Distortion in Black-Box Attacks
- Black-box adversarial attacks using Evolution Strategies
- Backdoor Attacks for Remote Sensing Data with Wavelet Transform
- Fooling a Real Car with Adversarial Traffic Signs
- Learnable Bernoulli Dropout for Bayesian Deep Learning
- Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
- Gradient Masking Causes CLEVER to Overestimate Adversarial Perturbation Size
- When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
- Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
- Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes
- Toward Scalable Verification for Safety-Critical Deep Networks
- Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization
- Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
- Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications
- On the Adversarial Robustness of Quantized Neural Networks
- What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
- A backdoor attack against LSTM-based text classification systems
- Improving Back-Propagation by Adding an Adversarial Gradient
- Online Deterministic Annealing for Classification and Clustering
- SAT: Improving Adversarial Training via Curriculum-Based Loss Smoothing
- Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
- White Paper Machine Learning in Certified Systems
- PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
- Classifier-agnostic saliency map extraction
- Interoceptive robustness through environment-mediated morphological development
- Image and Model Transformation with Secret Key for Vision Transformer
- Evaluating the visualization of what a Deep Neural Network has learned
- Lipschitz Properties for Deep Convolutional Networks
- Improving adversarial robustness of deep neural networks by using semantic information
- InfoAT: Improving Adversarial Training Using the Information Bottleneck Principle
- How Robust are Discriminatively Trained Zero-Shot Learning Models?
- Designing Perceptual Puzzles by Differentiating Probabilistic Programs
- Adversarial Defense by Latent Style Transformations
- Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization
- Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
- Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors
- Image Deconvolution with Deep Image and Kernel Priors
- Knowledge Cross-Distillation for Membership Privacy
- SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers
- Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks
- ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
- nuScenes Knowledge Graph -- A comprehensive semantic representation of traffic scenes for trajectory prediction
- Imperceptible Adversarial Examples by Spatial Chroma-Shift
- Detect & Reject for Transferability of Black-box Adversarial Attacks Against Network Intrusion Detection Systems
- Towards Analyzing Semantic Robustness of Deep Neural Networks
- Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
- Single-Node Attacks for Fooling Graph Neural Networks
- Does CLIP Know My Face?
- Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks
- Metamorphic Detection of Adversarial Examples in Deep Learning Models With Affine Transformations
- Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
- Adversarial Margin Maximization Networks
- Density of States Estimation for Out-of-Distribution Detection
- Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data
- A Spectral View of Adversarially Robust Features
- Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
- Physical Adversarial Attacks on Deep Neural Networks for Traffic Sign Recognition: A Feasibility Study
- Verification of Recurrent Neural Networks Through Rule Extraction
- Adversarial Detection and Correction by Matching Prediction Distributions
- AdvFAS: A robust face anti-spoofing framework against adversarial examples
- Security of Deep Learning based Lane Keeping System under Physical-World Adversarial Attack
- ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
- Prototype-based Neural Network Layers: Incorporating Vector Quantization
- Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency
- A Low-Cost Attack against the hCaptcha System
- Attacking Graph-based Classification via Manipulating the Graph Structure
- Web-Scale Training for Face Identification
- Annealing Optimization for Progressive Learning with Stochastic Approximation
- Large Margin Deep Networks for Classification
- Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
- AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
- The Convergence of Machine Learning and Communications
- Multitask Learning Strengthens Adversarial Robustness
- GreedyFool: Distortion-Aware Sparse Adversarial Attack
- Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
- Visualization Of Class Activation Maps To Explain AI Classification Of Network Packet Captures
- Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware
- Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense
- How adversarial attacks can disrupt seemingly stable accurate classifiers
- Adversarial Image Color Transformations in Explicit Color Filter Space
- PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning
- The gap between theory and practice in function approximation with deep neural networks
- Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations
- ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
- Defence against adversarial attacks using classical and quantum-enhanced Boltzmann machines
- Subverting Fair Image Search with Generative Adversarial Perturbations
- Identifying Audio Adversarial Examples via Anomalous Pattern Detection
- A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays
- Generating Image Adversarial Examples by Embedding Digital Watermarks
- The Feasibility and Inevitability of Stealth Attacks
- A Critical Reflection on the Use of Toxicity Detection Algorithms in Proactive Content Moderation Systems
- Perturbation Analysis of Gradient-based Adversarial Attacks
- FooBaR: Fault Fooling Backdoor Attack on Neural Network Training
- Backdoor Attacks on Crowd Counting
- Bridging the Performance Gap between FGSM and PGD Adversarial Training
- Appending Adversarial Frames for Universal Video Attack
- A Robust Adversarial Network-Based End-to-End Communications System With Strong Generalization Ability Against Adversarial Attacks
- Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller
- Overparameterized Linear Regression under Adversarial Attacks
- EREBA: Black-box Energy Testing of Adaptive Neural Networks
- HDXplore: Automated Blackbox Testing of Brain-Inspired Hyperdimensional Computing
- ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
- Spatio-Temporal Perturbations for Video Attribution
- A Survey of Behavior Learning Applications in Robotics -- State of the Art and Perspectives
- secml: A Python Library for Secure and Explainable Machine Learning
- Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising
- Manifold Regularization for Locally Stable Deep Neural Networks
- Morphology of three-body quantum states from machine learning
- Convergence and Margin of Adversarial Training on Separable Data
- Incorporating Unlabeled Data into Distributionally Robust Learning
- Generating Hard Examples for Pixel-wise Classification
- Detecting Adversarial Examples in Convolutional Neural Networks
- Eight challenges in developing theory of intelligence
- Scalable Verification of GNN-based Job Schedulers
- Block Switching: A Stochastic Approach for Deep Learning Security
- Beyond the Self: Using Grounded Affordances to Interpret and Describe Others' Actions
- Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
- Adversarial Attacks against Neural Networks in Audio Domain: Exploiting Principal Components
- Building Robust Deep Neural Networks for Road Sign Detection
- Lifecycle Management of Trustworthy AI Models in 6G Networks: The REASON Approach
- Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
- Jacobian Regularization for Mitigating Universal Adversarial Perturbations
- Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion
- Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
- Geometric robustness of deep networks: analysis and improvement
- Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization
- Robustness of Deep Neural Networks for Micro-Doppler Radar Classification
- Security and Machine Learning in the Real World
- Adversarial Attacks on Monocular Pose Estimation
- Adversarial Machine Learning Phases of Matter
- Bayesian Inference with Certifiable Adversarial Robustness
- Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks
- Optimal Transport as a Defense Against Adversarial Attacks
- Improved OOD Generalization via Adversarial Training and Pre-training
- Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
- A Visual Analytics Framework for Adversarial Text Generation
- On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems
- Adversarial Visual Robustness by Causal Intervention
- Bit Error Robustness for Energy-Efficient DNN Accelerators
- Decision-based Universal Adversarial Attack
- Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective
- Rare event failure test case generation in Learning-Enabled-Controllers
- GAP++: Learning to generate target-conditioned adversarial examples
- Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces
- Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness
- Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification
- Trust Region Based Adversarial Attack on Neural Networks
- An Efficient Adversarial Attack for Tree Ensembles
- On the Importance of Consistency in Training Deep Neural Networks
- Adversarial Attacks in a Multi-view Setting: An Empirical Study of the Adversarial Patches Inter-view Transferability
- CNNs Avoid Curse of Dimensionality by Learning on Patches
- PointCloud Saliency Maps
- Adversarial Robustness through the Lens of Convolutional Filters
- Generating Universal Adversarial Perturbations for Quantum Classifiers
- Towards Resistant Audio Adversarial Examples
- Towards Interpretable Face Recognition
- ToyArchitecture: Unsupervised Learning of Interpretable Models of the World
- Consistent Counterfactuals for Deep Models
- Deep Roto-Translation Scattering for Object Classification
- Relationship between manifold smoothness and adversarial vulnerability in deep learning with local errors
- Adversarial Exposure Attack on Diabetic Retinopathy Imagery Grading
- How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models
- HoneyModels: Machine Learning Honeypots
- Do Vision Models Encode Object-Level Semantic Relatedness? A Cognitive Psychology-Inspired Benchmark
- RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video Compression
- Security Consideration For Deep Learning-Based Image Forensics
- BASAR:Black-box Attack on Skeletal Action Recognition
- Improved Detection of Adversarial Images Using Deep Neural Networks
- From Heatmaps to Structural Explanations of Image Classifiers
- Exploring Adversarial Examples: Patterns of One-Pixel Attacks
- LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verification
- A Methodology to Identify Cognition Gaps in Visual Recognition Applications Based on Convolutional Neural Networks
- Offset-free setpoint tracking using neural network controllers
- Using Mode Connectivity for Loss Landscape Analysis
- Maximally Invariant Data Perturbation as Explanation
- Robust Proxy: Improving Adversarial Robustness by Robust Proxy Learning
- Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
- Recursive Inference for Variational Autoencoders
- Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
- From Hardware Fingerprint to Access Token: Enhancing the Authentication on IoT Devices
- SOAR: Second-Order Adversarial Regularization
- Adversarial Attack and Defense in Deep Ranking
- Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
- On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
- Stochastic Substitute Training: A Gray-box Approach to Craft Adversarial Examples Against Gradient Obfuscation Defenses
- Subset Scanning Over Neural Network Activations
- Gray-box Adversarial Testing for Control Systems with Machine Learning Component
- Physically Consistent Multiple-Step Data-Driven Predictions Using Physics-based Filters
- Provable Robustness Against a Union of Adversarial Attacks
- Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
- Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
- Engineering problems in machine learning systems
- Neural Networks with Structural Resistance to Adversarial Attacks
- Conv-Reluplex: A Verification Framework For Convolution Neural Networks
- Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework
- Fingerprinting Encrypted Voice Traffic on Smart Speakers with Deep Learning
- Generating Out of Distribution Adversarial Attack using Latent Space Poisoning
- Data-Dependent Randomized Smoothing
- Stress Test Evaluation of Biomedical Word Embeddings
- Adversarial joint attacks on legged robots
- Rearchitecting Classification Frameworks For Increased Robustness
- Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbations
- On the Robustness of Human Pose Estimation
- Improving Robustness and Generality of NLP Models Using Disentangled Representations
- Deep Learning in Robotics: A Review of Recent Research
- 3D Adversarial Attacks Beyond Point Cloud
- Blind Adversarial Network Perturbations
- Explaining Neural Networks Semantically and Quantitatively
- Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
- Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
- Using a GAN to Generate Adversarial Examples to Facial Image Recognition
- Noisy Computations during Inference: Harmful or Helpful?
- Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script
- Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
- 3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
- RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
- Benford's law: what does it say on adversarial images?
- Is Face Recognition Safe from Realizable Attacks?
- Preserving Semantics in Textual Adversarial Attacks
- Alternating Direction Method of Multipliers for Quantization
- On the relationship between class selectivity, dimensionality, and robustness
- mFI-PSO: A Flexible and Effective Method in Adversarial Image Generation for Deep Neural Networks
- Pelta: Shielding Transformers to Mitigate Evasion Attacks in Federated Learning
- Explainable and Trustworthy Traffic Sign Detection for Safe Autonomous Driving: An Inductive Logic Programming Approach
- Towards Audit Requirements for AI-based Systems in Mobility Applications
- Careful What You Wish For: on the Extraction of Adversarially Trained Models
- Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
- Physical machine learning outperforms "human learning" in Quantum Chemistry
- Synthesis-guided Adversarial Scenario Generation for Gray-box Feedback Control Systems with Sensing Imperfections
- On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services
- Intermediate Level Adversarial Attack for Enhanced Transferability
- AutoGAN: Robust Classifier Against Adversarial Attacks
- MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes
- Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
- Adversarial Robustness Guarantees for Gaussian Processes
- Stochastic Combinatorial Ensembles for Defending Against Adversarial Examples
- Scalable Attack on Graph Data by Injecting Vicious Nodes
- A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks
- kk2018 at SemEval-2020 Task 9: Adversarial Training for Code-Mixing Sentiment Classification
- Data Curation with Deep Learning [Vision]
- The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GAN
- Efficient Project Gradient Descent for Ensemble Adversarial Attack
- A Reflection on Learning from Data: Epistemology Issues and Limitations
- A4 : Evading Learning-based Adblockers
- Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers
- Low-Interception Waveform: To Prevent the Recognition of Spectrum Waveform Modulation via Adversarial Examples
- Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks
- A Self-supervised Approach for Adversarial Robustness
- Rethinking the Artificial Neural Networks: A Mesh of Subnets with a Central Mechanism for Storing and Predicting the Data
- Reducing Adversarially Robust Learning to Non-Robust PAC Learning
- Modularity Matters: Learning Invariant Relational Reasoning Tasks
- Analysis and Applications of Class-wise Robustness in Adversarial Training
- Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System
- Learning Automata Based Q-learning for Content Placement in Cooperative Caching
- Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness
- Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons
- Adversarial Attacks on Classifiers for Eye-based User Modelling
- Resilient Linear Classification: An Approach to Deal with Attacks on Training Data
- Modular Learning Component Attacks: Today's Reality, Tomorrow's Challenge
- Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
- Understanding Catastrophic Overfitting in Adversarial Training
- Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks
- Bayesian Reasoning with Trained Neural Networks
- Backpropagation for Implicit Spectral Densities
- A Singular Value Perspective on Model Robustness
- Preventing Clean Label Poisoning using Gaussian Mixture Loss
- Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack
- Attacking Optical Flow
- To Make Yourself Invisible with Adversarial Semantic Contours
- Class Subset Selection for Transfer Learning using Submodularity
- Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts
- Detecting Adversarial Patches with Class Conditional Reconstruction Networks
- Adversarial Feature Desensitization
- The Tensor Track VII: From Quantum Gravity to Artificial Intelligence
- Model Interpretability and Rationale Extraction by Input Mask Optimization
- A Robust Classification-autoencoder to Defend Outliers and Adversaries
- Robust Stability Analysis of Positive Lure System with Neural Network Feedback
- Regional Image Perturbation Reduces Norms of Adversarial Examples While Maintaining Model-to-model Transferability
- Classification Uncertainty of Deep Neural Networks Based on Gradient Information
- Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
- FedServing: A Federated Prediction Serving Framework Based on Incentive Mechanism
- Seeing eye-to-eye? A comparison of object recognition performance in humans and deep convolutional neural networks under image manipulation
- Seeing in the dark with recurrent convolutional neural networks
- Pretraining Image Encoders without Reconstruction via Feature Prediction Loss
- On Lipschitz Bounds of General Convolutional Neural Networks
- CAAD 2018: Iterative Ensemble Adversarial Attack
- Towards User Guided Actionable Recourse
- Live Trojan Attacks on Deep Neural Networks
- Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
- Natural Perturbed Training for General Robustness of Neural Network Classifiers
- Time-varying Gaussian Process Bandit Optimization with Non-constant Evaluation Time
- Lifted Regression/Reconstruction Networks
- torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Python
- Generalization Error Analysis of Neural networks with Gradient Based Regularization
- Adequacy of the Gradient-Descent Method for Classifier Evasion Attacks
- Toward Few-step Adversarial Training from a Frequency Perspective
- Learning Based on CC1 and CC4 Neural Networks
- A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks
- Coverage-Guaranteed Prediction Sets for Out-of-Distribution Data
- Feedback Techniques in Computer-Based Simulation Training: A Survey
- On the randomised stability constant for inverse problems
- MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization
- Patch augmentation: Towards efficient decision boundaries for neural networks
- Clarifying Myths About the Relationship Between Shape Bias, Accuracy, and Robustness
- Can Perceptual Guidance Lead to Semantically Explainable Adversarial Perturbations?
- Adversarial Edit Attacks for Tree Data
- Conditional Adversarial Camera Model Anonymization
- Natural Adversarial Objects
- ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems
- When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence
- Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models
- Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization
- A cryptographic approach to black box adversarial machine learning
- A Deep Value-network Based Approach for Multi-Driver Order Dispatching
- Who is Responsible for Adversarial Defense?
- Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
- Towards Safety Verification of Direct Perception Neural Networks
- Heat and Blur: An Effective and Fast Defense Against Adversarial Examples
- Real World Robustness from Systematic Noise
- Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness
- Being Single Has Benefits. Instance Poisoning to Deceive Malware Classifiers
- The Vulnerability of the Neural Networks Against Adversarial Examples in Deep Learning Algorithms
- Versatile Verification of Tree Ensembles
- Regularized Ensembles and Transferability in Adversarial Learning
- Adversarial Robustness on Image Classification with -means
- Robust Single-step Adversarial Training with Regularizer
- Exploring the Deep Feature Space of a Cell Classification Neural Network
- Comparing Reinforcement Learning and Human Learning using the Game of Hidden Rules
- Bio-inspired Robustness: A Review
- Fast Approximate Spectral Normalization for Robust Deep Neural Networks
- Enhance Diffusion to Improve Robust Generalization
- Can audio-visual integration strengthen robustness under multimodal attacks?
- The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
- Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
- Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees
- What do CNN neurons learn: Visualization & Clustering
- Rethinking Empirical Evaluation of Adversarial Robustness Using First-Order Attack Methods
- Access Control with Encrypted Feature Maps for Object Detection Models
- Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
- Visual Explanation for Identification of the Brain Bases for Dyslexia on fMRI Data
- A statistical framework for efficient out of distribution detection in deep neural networks
- Interpretabilité des modèles : état des lieux des méthodes et application à l'assurance
- Black-box Adversarial Sample Generation Based on Differential Evolution
- Analytical bounds on the local Lipschitz constants of affine-ReLU functions
- Towards Evaluating and Training Verifiably Robust Neural Networks
- Mapper Based Classifier
- Streaming Networks: Enable A Robust Classification of Noise-Corrupted Images
- Technical Report: When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks
- A Useful Taxonomy for Adversarial Robustness of Neural Networks
- MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
- The art of defense: letting networks fool the attacker
- Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
- Adversarial Jamming for a More Effective Constellation Attack
- Robustifying automatic speech recognition by extracting slowly varying features
- Search Space of Adversarial Perturbations against Image Filters
- Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping
- Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
- Online Black-Box Confidence Estimation of Deep Neural Networks
- Neural Belief Reasoner
- Minimum sharpness: Scale-invariant parameter-robustness of neural networks
- State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
- Towards Leveraging the Information of Gradients in Optimization-based Adversarial Attack
- And/or trade-off in artificial neurons: impact on adversarial robustness
- Warp: a method for neural network interpretability applied to gene expression profiles
- CNN-based Steganalysis and Parametric Adversarial Embedding: a Game-Theoretic Framework
- Delving into the pixels of adversarial samples
- Lethean Attack: An Online Data Poisoning Technique
- Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks
- Adversarial Attacks on Deep Models for Financial Transaction Records
- Understanding Convolutional Neural Networks with A Mathematical Model
- Intriguing Properties of Input-dependent Randomized Smoothing
- Synthetic Data Generation for Economists
- Understanding Misclassifications by Attributes
- Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection
- TEAM: An Taylor Expansion-Based Method for Generating Adversarial Examples
- Are L2 adversarial examples intrinsically different?
- Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs
- Counterfactual Explanations via Latent Space Projection and Interpolation
- Robust Deep Neural Networks Inspired by Fuzzy Logic
- Training Efficiency and Robustness in Deep Learning
- Explainability-Aware One Point Attack for Point Cloud Neural Networks
- Latent Cognizance: What Machine Really Learns
- Universal Stego Post-processing for Enhancing Image Steganography
- Architectural Resilience to Foreground-and-Background Adversarial Noise
- Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach
- Calibrated Adversarial Training
- Adversarially Robust Frame Sampling with Bounded Irregularities
- On Inductive Biases for Machine Learning in Data Constrained Settings
- Confidence Preservation Property in Knowledge Distillation Abstractions
- On educating machines
- A neural network model of perception and reasoning
- advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
- Amicable Aid: Perturbing Images to Improve Classification Performance
- Spatiotemporal Attacks for Embodied Agents
- Local Linearity and Double Descent in Catastrophic Overfitting
- Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers
- Wiggling Weights to Improve the Robustness of Classifiers
- Comments on Sejnowski's "The unreasonable effectiveness of deep learning in artificial intelligence" [arXiv:2002.04806]
- Simpler Certified Radius Maximization by Propagating Covariances
- Beyond Categorical Label Representations for Image Classification
- CodNN -- Robust Neural Networks From Coded Classification
- Recognition Awareness: An Application of Latent Cognizance to Open-Set Recognition
- Towards Optimal Randomized Strategies in Adversarial Example Game
- Low-Cost Transfer Learning of Face Tasks
- Understanding Robustness in Teacher-Student Setting: A New Perspective
- Improved Algorithms for White-Box Adversarial Streams
- A note on hyperparameters in black-box adversarial examples
- An Efficient Pre-processing Method to Eliminate Adversarial Effects
- Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods
- Boosting the Robustness Verification of DNN by Identifying the Achilles's Heel
- Defenses Against Multi-Sticker Physical Domain Attacks on Classifiers
- Towards Robust Neural Networks with Lipschitz Continuity
- Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification
- Modelling Identity Rules with Neural Networks
- Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
- Adversarial Detection by Approximation of Ensemble Boundary
- Decoder-free Robustness Disentanglement without (Additional) Supervision
- Leaky ReLUs That Differ in Forward and Backward Pass Facilitate Activation Maximization in Deep Neural Networks
- Leave-one-out Unfairness
- On Configurable Defense against Adversarial Example Attacks
- Semantic Network Interpretation
- Boosting Black-Box Adversarial Attacks with Meta Learning