MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
원문 초록
Deep neural networks (DNNs) are vulnerable to adversarial perturbation, where an imperceptible perturbation is added to the image that can fool the DNNs. Diffusion-based adversarial purification focuses on using the diffusion model to generate a clean image against such adversarial attacks. Unfortunately, the generative process of the diffusion model is also inevitably affected by adversarial perturbation since the diffusion model is also a deep network where its input has adversarial perturbation. In this work, we propose MimicDiffusion, a new diffusion-based adversarial purification technique, that directly approximates the generative process of the diffusion model with the clean image as input. Concretely, we analyze the differences between the guided terms using the clean image and the adversarial sample. After that, we first implement MimicDiffusion based on Manhattan distance. Then, we propose two guidance to purify the adversarial perturbation and approximate the clean diffusion model. Extensive experiments on three image datasets including CIFAR-10, CIFAR-100, and ImageNet with three classifier backbones including WideResNet-70-16, WideResNet-28-10, and ResNet50 demonstrate that MimicDiffusion significantly performs better than the state-of-the-art baselines. On CIFAR-10, CIFAR-100, and ImageNet, it achieves 92.67\%, 61.35\%, and 61.53\% average robust accuracy, which are 18.49\%, 13.23\%, and 17.64\% higher, respectively. The code is available in the supplementary material.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FlowPure: Continuous Normalizing Flows for Adversarial Purification
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks
Random Sampling for Diffusion-based Adversarial Purification
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.