paper-with-me

Papers

Towards more transferable adversarial attack in black-box manner

2025-05-23 · Chun Tong Lei, Zhongliang Guo, Hon Chung Lee, Minh Quoc Duong, Chun Pong Lau

Adversarial attacks have become a well-explored domain, frequently serving as evaluation baselines for model robustness. Among these, black-box attacks based on transferability have received significant attention due to their practical applicability in real-world scenarios. Traditional black-box methods have generally focused on improving the optimization framework (e.g., utilizing momentum in MI-FGSM) to enhance transferability, rather than examining the dependency on surrogate white-box model architectures. Recent state-of-the-art approach DiffPGD has demonstrated enhanced transferability by employing diffusion-based adversarial purification models for adaptive attacks. The inductive bias of diffusion-based adversarial purification aligns naturally with the adversarial attack process, where both involving noise addition, reducing dependency on surrogate white-box model selection. However, the denoising process of diffusion models incurs substantial computational costs through chain rule derivation, manifested in excessive VRAM consumption and extended runtime. This progression prompts us to question whether introducing diffusion models is necessary. We hypothesize that a model sharing similar inductive bias to diffusion-based adversarial purification, combined with an appropriate loss function, could achieve comparable or superior transferability while dramatically reducing computational overhead. In this paper, we propose a novel loss function coupled with a unique surrogate model to validate our hypothesis. Our approach leverages the score of the time-dependent classifier from classifier-guided diffusion models, effectively incorporating natural data distribution knowledge into the adversarial optimization process. Experimental results demonstrate significantly improved transferability across diverse model architectures while maintaining robustness against diffusion-based defenses.

📄 PDF Abstract BibTeX arXiv:2505.18097

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial PurificationDenoisingInductive BiasModel Selection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 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

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

2025-05-11 · Xia Du, JiaJie Zhu, Jizhe Zhou, Chi-Man Pun 외

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malici…

Relevance Attack on Detectors

2020-08-16 · Sizhe Chen, Fan He, Xiaolin Huang, Kun Zhang

This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue…

Autonomous DrivingDiversityInstance Segmentationobject-detection+3

Towards Transferable Targeted Attack

2020-06-01 · CVPR 2020 6 · Maosen Li, Cheng Deng, Tengjiao Li, Junchi Yan 외

An intriguing property of adversarial examples is their transferability, which suggests that black-box attacks are feasible in real-world applications. Previous works mostly study the transferability on non-targeted sett…

Metric Learning

A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications

2023-09-21 · NeurIPS 2023 11

Transfer-based attacks are a practical method of black-box adversarial attacks, in which the attacker aims to craft adversarial examples from a source (surrogate) model that is transferable to the target model. A wide ra…

Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning

2020-08-25 · Yinghua Zhang, Yangqiu Song, Jian Liang, Kun Bai 외

Transfer learning has become a common practice for training deep learning models with limited labeled data in a target domain. On the other hand, deep models are vulnerable to adversarial attacks. Though transfer learnin…

Transfer Learning