paper-with-me

Papers

Adversarial Eigen Attack on Black-Box Models

2020-08-27 · CVPR 2022 1 · Linjun Zhou, Peng Cui, Yinan Jiang, Shiqiang Yang

Black-box adversarial attack has attracted a lot of research interests for its practical use in AI safety. Compared with the white-box attack, a black-box setting is more difficult for less available information related to the attacked model and the additional constraint on the query budget. A general way to improve the attack efficiency is to draw support from a pre-trained transferable white-box model. In this paper, we propose a novel setting of transferable black-box attack: attackers may use external information from a pre-trained model with available network parameters, however, different from previous studies, no additional training data is permitted to further change or tune the pre-trained model. To this end, we further propose a new algorithm, EigenBA to tackle this problem. Our method aims to explore more gradient information of the black-box model, and promote the attack efficiency, while keeping the perturbation to the original attacked image small, by leveraging the Jacobian matrix of the pre-trained white-box model. We show the optimal perturbations are closely related to the right singular vectors of the Jacobian matrix. Further experiments on ImageNet and CIFAR-10 show that even the unlearnable pre-trained white-box model could also significantly boost the efficiency of the black-box attack and our proposed method could further improve the attack efficiency.

📄 PDF Abstract BibTeX arXiv:2009.00097

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Energy Attack: On Transferring Adversarial Examples

2021-09-09 · Ruoxi Shi, Borui Yang, Yangzhou Jiang, Chenglong Zhao 외

In this work we propose Energy Attack, a transfer-based black-box $L_\infty$-adversarial attack. The attack is parameter-free and does not require gradient approximation. In particular, we first obtain white-box adversar…

Adversarial Attack

Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection

2023-12-12 · Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jorg S. Wicker

With the advancement in robotics, it is becoming increasingly common for large factories and warehouses to incorporate visual SLAM (vSLAM) enabled automated robots that operate closely next to humans. This makes any adve…

Loop Closure Detection

The Adversarial Attack and Detection under the Fisher Information Metric

2018-10-09 · Chenxiao Zhao, P. Thomas Fletcher, Mixue Yu, Yaxin Peng 외

Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information g…

Adversarial Attack

Graph Structural Attack by Perturbing Spectral Distance

2021-11-01 · Lu Lin, Ethan Blaser, Hongning Wang

Graph Convolutional Networks (GCNs) have fueled a surge of research interest due to their encouraging performance on graph learning tasks, but they are also shown vulnerability to adversarial attacks. In this paper, an e…

Graph Learning

EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models

2025-02-20 · Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya 외

Vision-Language Models (VLMs) inherit adversarial vulnerabilities of Large Language Models (LLMs), which are further exacerbated by their multimodal nature. Existing defenses, including adversarial training, input transf…