Sparse Coding Frontend for Robust Neural Networks
arXiv:2104.05353
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.
International Conference on Learning Representations (ICLR) 2021 Workshop on Security and Safety in Machine Learning Systems
References in corpus (6)
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- Theoretically Principled Trade-off between Robustness and Accuracy
- On Evaluating Adversarial Robustness
- The Space of Transferable Adversarial Examples
- Countering Adversarial Images using Input Transformations
- ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation