File(s) under permanent embargo
Reason: Publisher requirement. Embargo will be lifted after publication.
Guided diffusion-based adversarial purification model with denoised prior constraint
Adversarial attack has posed a significant threat to modern deep learning based models. Recently, various adversarial defending algorithms are proposed to tackle the problem.
Among them, diffusion-based adversarial purification approaches offer the most promising solutions. However, their effectiveness are limited due to the strong adversarial perturbations presented in attacked images. These adversarial signals hinder the introduction of guidance into diffusion models in order to improve the defence efficacy. In this paper, we propose a novel approach to embed reliable guidance into diffusion-based adversarial purification model to improve both its defence effectiveness and efficiency. In specific, we present a diffusion sampling guidance enhanced by a pretrained denoising network as a prior constraint to improve the adversarial defence performance. Experimental results convincingly demonstrate the superior performance of the proposed approach in terms of enhanced robustness to standard image classifiers when compared to state-of-the-art adversarial defence approaches.
History
School
- Science
Department
- Computer Science
Published in
International Joint Conference on Neural NetworksSource
International Joint Conference on Neural NetworksPublisher
IEEEVersion
- AM (Accepted Manuscript)
Publisher statement
Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Acceptance date
2024-03-15Publisher version
Language
- en