paper-with-me

Papers

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

2023-12-08 · CVPR 2024 1 · Kaiyu Song, Hanjiang Lai

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.

📄 PDF Abstract BibTeX arXiv:2312.04802

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Purification

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

2024-03-18 · CVPR 2024 1 · Linyu Tang, Lei Zhang

Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to subtle adversarial perturbations, prompting the development of many advanced adversarial defense methods aimed at mitigating adversa…

Adversarial AttackAdversarial DefenseAdversarial PurificationAdversarial Robustness

Purifying Adversarial Perturbation with Adversarially Trained Auto-encoders

2019-05-26 · Hebi Li, Qi Xiao, Shixin Tian, Jin Tian

Machine learning models are vulnerable to adversarial examples. Iterative adversarial training has shown promising results against strong white-box attacks. However, adversarial training is very expensive, and every time…

BIG-bench Machine Learning

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias

2023-05-08 · Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng 외

Pre-trained Language Models (PLMs) may be poisonous with backdoors or bias injected by the suspicious attacker during the fine-tuning process. A core challenge of purifying potentially poisonous PLMs is precisely finding…

Large Language Model Sentinel: LLM Agent for Adversarial Purification

2024-05-24 · Guang Lin, Toshihisa Tanaka, Qibin Zhao

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by …

Adversarial DefenseAdversarial PurificationAdversarial RobustnessLanguage Modeling+3

Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs

2025-06-01 · Yudong Zhang, Ruobing Xie, Yiqing Huang, Jiansheng Chen 외

Recent advances in large vision-language models (LVLMs) have showcased their remarkable capabilities across a wide range of multimodal vision-language tasks. However, these models remain vulnerable to visual adversarial …

Adversarial PurificationComputational Efficiency