Adversarial Examples: Attacks and Defenses for Deep Learning

Abstract

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples and explore the challenges and the potential solutions.

arXiv commentGithub: https://github.com/chbrian/awesome-adversarial-examples-dl

References in corpus (55)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Sequence to Sequence Learning with Neural Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Deep Learning with Differential Privacy
• WaveNet: A Generative Model for Raw Audio
• Striving for Simplicity: The All Convolutional Net
• Ensemble Adversarial Training: Attacks and Defenses
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Do Deep Nets Really Need to be Deep?
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• NIPS 2016 Tutorial: Generative Adversarial Networks
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Delving into Transferable Adversarial Examples and Black-box Attacks
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Opening the Black Box of Deep Neural Networks via Information
• Poisoning Attacks against Support Vector Machines
• Autoencoding beyond pixels using a learned similarity metric
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Adversarially Robust Generalization Requires More Data
• Robust Physical-World Attacks on Deep Learning Models
• Understanding Neural Networks through Representation Erasure
• Generating Natural Adversarial Examples
• YOLO9000: Better, Faster, Stronger
• The Space of Transferable Adversarial Examples
• Adversarial Machine Learning at Scale
• Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN
• On the (Statistical) Detection of Adversarial Examples
• PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
• Is feature selection secure against training data poisoning?
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Learning with a Strong Adversary
• Adversarial vulnerability for any classifier
• MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
• Early Methods for Detecting Adversarial Images
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• Delving into adversarial attacks on deep policies
• Towards Proving the Adversarial Robustness of Deep Neural Networks
• Provably Minimally-Distorted Adversarial Examples
• Adversarial Examples for Semantic Segmentation and Object Detection
• Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
• Deep Neural Network Based Malware Detection Using Two Dimensional Binary Program Features
• Adversarial Images for Variational Autoencoders
• DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
• Standard detectors aren't (currently) fooled by physical adversarial stop signs
• Boosting Adversarial Attacks with Momentum
• DeepDGA: Adversarially-Tuned Domain Generation and Detection
• Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight
• Adversarial examples for generative models
• Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection
• Towards Robust Detection of Adversarial Examples

Cited by in corpus (51)

• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Flow-based Network Traffic Generation using Generative Adversarial Networks
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
• Deceiving End-to-End Deep Learning Malware Detectors using Adversarial Examples
• Training verified learners with learned verifiers
• Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness
• Towards Demystifying Membership Inference Attacks
• Contrastive Learning with Adversarial Examples
• Characterizing the Decision Boundary of Deep Neural Networks
• Defending against Adversarial Images using Basis Functions Transformations
• Enhancing Adversarial Example Transferability with an Intermediate Level Attack
• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• Deep neural network enabled corrective source term approach to hybrid analysis and modeling
• Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing
• Software Testing for Machine Learning
• Robust Conditional Generative Adversarial Networks
• CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks
• Say What I Want: Towards the Dark Side of Neural Dialogue Models
• Non-Negative Networks Against Adversarial Attacks
• Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection
• Feature Unlearning for Pre-trained GANs and VAEs
• Adaptive Generation of Unrestricted Adversarial Inputs
• How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models
• ATMPA: Attacking Machine Learning-based Malware Visualization Detection Methods via Adversarial Examples
• Effects of Loss Functions And Target Representations on Adversarial Robustness
• Strength in Numbers: Trading-off Robustness and Computation via Adversarially-Trained Ensembles
• Fibres of Failure: Classifying errors in predictive processes
• Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
• Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
• Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
• A randomized gradient-free attack on ReLU networks
• BUZz: BUffer Zones for defending adversarial examples in image classification
• ATRO: Adversarial Training with a Rejection Option
• Analysis Methods in Neural Language Processing: A Survey
• Classification Uncertainty of Deep Neural Networks Based on Gradient Information
• Adversarial Attack Type I: Cheat Classifiers by Significant Changes
• Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehension
• Connecting Lyapunov Control Theory to Adversarial Attacks
• Hacking Neural Networks: A Short Introduction
• VisBERT: Hidden-State Visualizations for Transformers
• Adversarial training applied to Convolutional Neural Network for photometric redshift predictions
• Feedback Learning for Improving the Robustness of Neural Networks
• Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
• Contextual Fusion For Adversarial Robustness
• And/or trade-off in artificial neurons: impact on adversarial robustness
• Adversarial Attacks on Cognitive Self-Organizing Networks: The Challenge and the Way Forward
• FUNN: Flexible Unsupervised Neural Network
• HAWKEYE: Adversarial Example Detector for Deep Neural Networks
• Doubly-Trained Adversarial Data Augmentation for Neural Machine Translation