ADBM: Adversarial diffusion bridge model for reliable adversarial purification
Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs the original pre-trained diffusion models for adversarial purification, to be suboptimal. This is due to an inherent trade-off between noise purification performance and data recovery quality. Additionally, the reliability of existing evaluations for DiffPure is questionable, as they rely on weak adaptive attacks. In this work, we propose a novel Adversarial Diffusion Bridge Model, termed ADBM. ADBM directly constructs a reverse bridge from the diffused adversarial data back to its original clean examples, enhancing the purification capabilities of the original diffusion models. Through theoretical analysis and experimental validation across various scenarios, ADBM has proven to be a superior and robust defense mechanism, offering significant promise for practical applications.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial PurificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DBLP: Noise Bridge Consistency Distillation For Efficient And Reliable Adversarial Purification
Recent advances in deep neural networks (DNNs) have led to remarkable success across a wide range of tasks. However, their susceptibility to adversarial perturbations remains a critical vulnerability. Existing diffusion-…
Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations. Adversarial approaches require target-domain adversarial loss during training, whic…
Image-to-Image TranslationClosing the Distribution Gap in Adversarial Training for LLMs
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerable to simple in-distribution exploits, s…
Adversarial RobustnessCATformer: Contrastive Adversarial Transformer for Image Super-Resolution
Super-resolution remains a promising technique to enhance the quality of low-resolution images. This study introduces CATformer (Contrastive Adversarial Transformer), a novel neural network integrating diffusion-inspired…
Image Super-ResolutionContrastive LearningDIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
Adversarial attacks, particularly patch attacks, pose significant threats to the robustness and reliability of deep learning models. Developing reliable defenses against patch attacks is crucial for real-world applicatio…
Adversarial DefenseFace Recognitionimage-classificationImage Classification