Adversarial Training against Location-Optimized Adversarial Patches

Abstract

Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work proposed so-called adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. These patches can easily be printed and applied in the physical world. While defenses against imperceptible adversarial examples have been studied extensively, robustness against adversarial patches is poorly understood. In this work, we first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. Then, we apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB. Additionally, in contrast to adversarial training on imperceptible adversarial examples, our adversarial patch training does not reduce accuracy.

arXiv comment20 pages, 6 tables, 4 figures, 2 algorithms, European Conference on Computer Vision Workshops 2020

References in corpus (37)

• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Theoretically Principled Trade-off between Robustness and Accuracy
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• Fast is better than free: Revisiting adversarial training
• Generating Natural Adversarial Examples
• Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
• Distributional Smoothing with Virtual Adversarial Training
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• Learning with a Strong Adversary
• Spatially Transformed Adversarial Examples
• Defensive Distillation is Not Robust to Adversarial Examples
• Are Labels Required for Improving Adversarial Robustness?
• Simple Black-box Adversarial Attacks
• LaVAN: Localized and Visible Adversarial Noise
• MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
• Adversarial Training Can Hurt Generalization
• On Physical Adversarial Patches for Object Detection
• On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
• Structured Adversarial Attack: Towards General Implementation and Better Interpretability
• Biologically inspired protection of deep networks from adversarial attacks
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Attacking the Madry Defense Model with $L_1$-based Adversarial Examples
• Evaluating and Understanding the Robustness of Adversarial Logit Pairing
• Certified Defenses for Adversarial Patches
• Adversarial Robustness Against the Union of Multiple Perturbation Models
• Unrestricted Adversarial Examples
• Exploring the Space of Black-box Attacks on Deep Neural Networks
• Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
• The Limitations of Adversarial Training and the Blind-Spot Attack
• Logit Pairing Methods Can Fool Gradient-Based Attacks
• Comment on "Biologically inspired protection of deep networks from adversarial attacks"
• Robustness of Rotation-Equivariant Networks to Adversarial Perturbations
• Manifold Adversarial Learning
• Enhanced Attacks on Defensively Distilled Deep Neural Networks
• Recovery Guarantees for Compressible Signals with Adversarial Noise
• Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks

Cited by in corpus (6)

• PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking
• Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame
• PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
• A Real-time Defense against Website Fingerprinting Attacks
• PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing
• Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition