Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness
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 suitable pre-processing. Diffusion models have been shown to be effective for adversarial purification. Despite their success, many aspects of diffusion purification still remain unexplored. In this paper, we investigate and improve upon three limiting designs of diffusion purification: the use of an improved diffusion model, advanced numerical simulation techniques, and optimal control of randomness. Based on our findings, we propose Purify++, a new diffusion purification algorithm that is now the state-of-the-art purification method against several adversarial attacks. Our work presents a systematic exploration of the limits of diffusion purification methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial PurificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Instant Adversarial Purification with Adversarial Consistency Distillation
Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise. Although some diffusion-based purification me…
Adversarial Purificationimage-classificationImage ClassificationPurify Once, Edit Freely: Breaking Image Protections under Model Mismatch
Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation. To mitigate these risks, proactive image protection methods embed small, often …
Image EditingTowards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Diffusion-Based Purification (DBP) has emerged as an effective defense mechanism against adversarial attacks. The efficacy of DBP has been attributed to the forward diffusion process, which narrows the distribution gap b…
Adversarial PurificationDenoisingMimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
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 PurificationDiffusion-Based Adversarial Purification for Speaker Verification
Recently, automatic speaker verification (ASV) based on deep learning is easily contaminated by adversarial attacks, which is a new type of attack that injects imperceptible perturbations to audio signals so as to make A…
Adversarial PurificationDenoisingSpeaker Verification