paper-with-me

Papers

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

2024-08-12 · Mingkun Zhang, Jianing Li, Wei Chen, Jiafeng Guo, Xueqi Cheng

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods.

📄 PDF Abstract BibTeX arXiv:2408.05900

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial PurificationAdversarial RobustnessDenoisingimage-classificationImage Classification

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

Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness

2023-10-28 · Boya Zhang, Weijian Luo, Zhihua Zhang

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suit…

Adversarial Purification

Guided Diffusion Model for Adversarial Purification

2022-05-30 · Jinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai 외

With wider application of deep neural networks (DNNs) in various algorithms and frameworks, security threats have become one of the concerns. Adversarial attacks disturb DNN-based image classifiers, in which attackers ca…

Adversarial PurificationDenoisingmodel

Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models

2023-11-13 · Yuanbin Cheng, Koji Yamashita, Jim Follum, Nanpeng Yu

The global deployment of the phasor measurement units (PMUs) enables real-time monitoring of the power system, which has stimulated considerable research into machine learning-based models for event detection and classif…

Adversarial PurificationComputational EfficiencyEvent Detection

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models

2024-08-31 · Hossein Khalili, Seongbin Park, Vincent Li, Brandan Bright 외

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbation…

Adversarial RobustnessComputational EfficiencyGenerative Adversarial Network

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 diff…

Adversarial Purification