Sparse Coding Frontend for Robust Neural Networks

Abstract

Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations. The current most effective defense methods against these adversarial attacks are variants of adversarial training. In this paper, we introduce a radically different defense trained only on clean images: a sparse coding based frontend which significantly attenuates adversarial attacks before they reach the classifier. We evaluate our defense on CIFAR-10 dataset under a wide range of attack types (including Linf , L2, and L1 bounded attacks), demonstrating its promise as a general-purpose approach for defense.

arXiv commentInternational Conference on Learning Representations (ICLR) 2021 Workshop on Security and Safety in Machine Learning Systems

References in corpus (11)

• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Theoretically Principled Trade-off between Robustness and Accuracy
• On Evaluating Adversarial Robustness
• The Space of Transferable Adversarial Examples
• Countering Adversarial Images using Input Transformations
• Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
• Parseval Networks: Improving Robustness to Adversarial Examples
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Torchattacks: A PyTorch Repository for Adversarial Attacks
• ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation