Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation
This addresses the vulnerability of deep neural networks to adversarial attacks by providing a versatile purification technique that generalizes across various threats and tasks, though it appears incremental as it builds on tensor network decompositions.
The paper tackles the problem of adversarial attacks on deep neural networks by proposing Tensor Network Purification (TNP), a model-free method that reconstructs clean examples from adversarial inputs without relying on specific attacks or datasets, achieving strong robustness across diverse scenarios as demonstrated on CIFAR-10, CIFAR-100, and ImageNet.
Deep neural networks are known to be vulnerable to well-designed adversarial attacks. Although numerous defense strategies have been proposed, many are tailored to the specific attacks or tasks and often fail to generalize across diverse scenarios. In this paper, we propose Tensor Network Purification (TNP), a novel model-free adversarial purification method by a specially designed tensor network decomposition algorithm. TNP depends neither on the pre-trained generative model nor the specific dataset, resulting in strong robustness across diverse adversarial scenarios. To this end, the key challenge lies in relaxing Gaussian-noise assumptions of classical decompositions and accommodating the unknown distribution of adversarial perturbations. Unlike the low-rank representation of classical decompositions, TNP aims to reconstruct the unobserved clean examples from an adversarial example. Specifically, TNP leverages progressive downsampling and introduces a novel adversarial optimization objective to address the challenge of minimizing reconstruction error but without inadvertently restoring adversarial perturbations. Extensive experiments conducted on CIFAR-10, CIFAR-100, and ImageNet demonstrate that our method generalizes effectively across various norm threats, attack types, and tasks, providing a versatile and promising adversarial purification technique.