advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch

Abstract

advertorch is a toolbox for adversarial robustness research. It contains various implementations for attacks, defenses and robust training methods. advertorch is built on PyTorch (Paszke et al., 2017), and leverages the advantages of the dynamic computational graph to provide concise and efficient reference implementations. The code is licensed under the LGPL license and is open sourced at https://github.com/BorealisAI/advertorch .

References in corpus (18)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Countering Adversarial Images using Input Transformations
• Detecting Adversarial Samples from Artifacts
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• A study of the effect of JPG compression on adversarial images
• Spatially Transformed Adversarial Examples
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Adversarial Manipulation of Deep Representations
• Classification regions of deep neural networks

Cited by in corpus (50)

• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• RobustBench: a standardized adversarial robustness benchmark
• MMA Training: Direct Input Space Margin Maximization through Adversarial Training
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• Controlling Neural Level Sets
• DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
• Batch Normalization is a Cause of Adversarial Vulnerability
• Mutual Adversarial Training: Learning together is better than going alone
• Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
• Incentives for Federated Learning: a Hypothesis Elicitation Approach
• Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Data
• Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints
• DaST: Data-free Substitute Training for Adversarial Attacks
• Transferable Universal Adversarial Perturbations Using Generative Models
• Voting based ensemble improves robustness of defensive models
• Adversarial Example Games
• TOP: Backdoor Detection in Neural Networks via Transferability of Perturbation
• Evaluating Robustness to Context-Sensitive Feature Perturbations of Different Granularities
• Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space
• Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
• Decision-based Universal Adversarial Attack
• Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks
• Instance Correction for Learning with Open-set Noisy Labels
• SEC4SR: A Security Analysis Platform for Speaker Recognition
• SOAR: Second-Order Adversarial Regularization
• Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
• PAC Prediction Sets Under Covariate Shift
• Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
• Toward Adversarial Robustness via Semi-supervised Robust Training
• Adversarial Attacks on Co-Occurrence Features for GAN Detection
• Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
• Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks
• Beneficial Perturbations Network for Defending Adversarial Examples
• Adversarial Attack on Deep Product Quantization Network for Image Retrieval
• Adversarial Feature Desensitization
• Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks
• Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
• Adversarial Learning with Cost-Sensitive Classes
• Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attacks
• Adversarial robustness via stochastic regularization of neural activation sensitivity
• Rethinking Empirical Evaluation of Adversarial Robustness Using First-Order Attack Methods
• A Study on the Uncertainty of Convolutional Layers in Deep Neural Networks
• Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty
• Adversarial Imitation Attack
• Orthogonal Deep Models As Defense Against Black-Box Attacks
• Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness
• Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
• Constraining Logits by Bounded Function for Adversarial Robustness
• Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions