paper-with-me

홈 › Papers

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

2023-03-22 · CVPR 2023 1 · Zexin Li, Bangjie Yin, Taiping Yao, Juefeng Guo, Shouhong Ding, Simin Chen, Cong Liu

A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i.e., inaccessible gradient and parameter information to attackers. While recent research took an important step towards attacking black-box FR models through leveraging transferability, their performance is still limited, especially against online commercial FR systems that can be pessimistic (e.g., a less than 50% ASR--attack success rate on average). Motivated by this, we present Sibling-Attack, a new FR attack technique for the first time explores a novel multi-task perspective (i.e., leveraging extra information from multi-correlated tasks to boost attacking transferability). Intuitively, Sibling-Attack selects a set of tasks correlated with FR and picks the Attribute Recognition (AR) task as the task used in Sibling-Attack based on theoretical and quantitative analysis. Sibling-Attack then develops an optimization framework that fuses adversarial gradient information through (1) constraining the cross-task features to be under the same space, (2) a joint-task meta optimization framework that enhances the gradient compatibility among tasks, and (3) a cross-task gradient stabilization method which mitigates the oscillation effect during attacking. Extensive experiments demonstrate that Sibling-Attack outperforms state-of-the-art FR attack techniques by a non-trivial margin, boosting ASR by 12.61% and 55.77% on average on state-of-the-art pre-trained FR models and two well-known, widely used commercial FR systems.

📄 PDF Abstract BibTeX arXiv:2303.12512

Code (1)

Tencent/TFace/tree/Adv-Attack-Defense/security/tasks/Adv-Attack-Defense/Sibling-Attack 공식 구현 pytorch

Tasks

Adversarial AttackAttributeFace Recognition

Similar Papers 제목 키워드 기반

Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective

2026-01-30 · Keke Tang, Xianheng Liu, Weilong Peng, Xiaofei Wang 외 arxiv

Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink a…

Point Clouds

Rethinking Adversarial Transferability from a Data Distribution Perspective

2021-09-29 · ICLR 2022 4 · Yao Zhu, Jiacheng Sun, Zhenguo Li

Adversarial transferability enables attackers to generate adversarial examples from the source model to attack the target model, which has raised security concerns about the deployment of DNNs in practice. In this paper,…

Adversarial Attack

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

2023-03-16 · Huanran Chen, Yichi Zhang, Yinpeng Dong, Xiao Yang 외

It is widely recognized that deep learning models lack robustness to adversarial examples. An intriguing property of adversarial examples is that they can transfer across different models, which enables black-box attacks…

image-classificationImage ClassificationLanguage Modellingmodel+2

Towards Efficient Data Free Black-Box Adversarial Attack

2022-01-01 · CVPR 2022 1 · Jie Zhang, Bo Li, Jianghe Xu, Shuang Wu 외

Classic black-box adversarial attacks can take advantage of transferable adversarial examples generated by a similar substitute model to successfully fool the target model. However, these substitute models need to be…

Adversarial Attack

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks

2025-01-02 · Teng Li, Xingjun Ma, Yu-Gang Jiang

Transferable adversarial examples highlight the vulnerability of deep neural networks (DNNs) to imperceptible perturbations across various real-world applications. While there have been notable advancements in untargeted…