paper-with-me

Papers

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment

2025-06-02 · Kaixun Jiang, Zhaoyu Chen, Haijing Guo, Jinglun Li, Jiyuan Fu, Pinxue Guo, Hao Tang, Bo Li, Wenqiang Zhang

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with adversary preferences. Unlike benign alignment, adversarial alignment involves two inherently conflicting preferences: visual consistency and attack effectiveness, which often lead to unstable optimization and reward hacking (e.g., reducing visual quality to improve attack success). To address this, we propose APA (Adversary Preferences Alignment), a two-stage framework that decouples conflicting preferences and optimizes each with differentiable rewards. In the first stage, APA fine-tunes LoRA to improve visual consistency using rule-based similarity reward. In the second stage, APA updates either the image latent or prompt embedding based on feedback from a substitute classifier, guided by trajectory-level and step-wise rewards. To enhance black-box transferability, we further incorporate a diffusion augmentation strategy. Experiments demonstrate that APA achieves significantly better attack transferability while maintaining high visual consistency, inspiring further research to approach adversarial attacks from an alignment perspective. Code will be available at https://github.com/deep-kaixun/APA.

📄 PDF Abstract BibTeX arXiv:2506.01511

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

APA 설명 없음
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

ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack

2024-08-10 · Ziyi Gao, Kai Chen, Zhipeng Wei, Tingshu Mou 외

Recent diffusion-based unrestricted attacks generate imperceptible adversarial examples with high transferability compared to previous unrestricted attacks and restricted attacks. However, existing works on diffusion-bas…

Adversarial AttackDenoising

Content-based Unrestricted Adversarial Attack

2023-05-18 · NeurIPS 2023 11

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to de…

Adversarial Attack

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

2023-07-24 · Xuelong Dai, Kaisheng Liang, Bin Xiao

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass …

Adversarial AttackAdversarial Defense

Gradient-Free Adversarial Purification with Diffusion Models

2025-01-23 · Xuelong Dai, Dong Wang, Duan Mingxing, Bin Xiao

Adversarial training and adversarial purification are two effective and practical defense methods to enhance a model's robustness against adversarial attacks. However, adversarial training necessitates additional trainin…

Adversarial DefenseAdversarial PurificationSuper-Resolution

SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples

2025-07-10 · Dren Fazlija, Monty-Maximilian Zühlke, Johanna Schrader, Arkadij Orlov 외

Unrestricted adversarial attacks aim to fool computer vision models without being constrained by $\ell_p$-norm bounds to remain imperceptible to humans, for example, by changing an object's color. This allows attackers t…