paper-with-me

홈 › Papers

Energy Attack: On Transferring Adversarial Examples

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

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 adversarial perturbations of a surrogate model and divide these perturbations into small patches. Then we extract the unit component vectors and eigenvalues of these patches with principal component analysis (PCA). Base on the eigenvalues, we can model the energy distribution of adversarial perturbations. We then perform black-box attacks by sampling from the perturbation patches according to their energy distribution, and tiling the sampled patches to form a full-size adversarial perturbation. This can be done without the available access to victim models. Extensive experiments well demonstrate that the proposed Energy Attack achieves state-of-the-art performance in black-box attacks on various models and several datasets. Moreover, the extracted distribution is able to transfer among different model architectures and different datasets, and is therefore intrinsic to vision architectures.

📄 PDF Abstract BibTeX arXiv:2109.04300

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training

2018-03-14 · Derek Wang, Chaoran Li, Sheng Wen, Surya Nepal 외

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been propo…

Adversarial Attack

Fast Local Attack: Generating Local Adversarial Examples for Object Detectors

2020-10-27 · Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu 외

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor…

Object

ReFace: Real-time Adversarial Attacks on Face Recognition Systems

2022-06-09 · Shehzeen Hussain, Todd Huster, Chris Mesterharm, Paarth Neekhara 외

Deep neural network based face recognition models have been shown to be vulnerable to adversarial examples. However, many of the past attacks require the adversary to solve an input-dependent optimization problem using g…

Face IdentificationFace RecognitionFace Verification

Transferable Adversarial Perturbations

2018-09-01 · ECCV 2018 9 · Wen Zhou, Xin Hou, Yongjun Chen, Mengyun Tang 외

State-of-the-art deep neural network classifiers are highly vulnerable to adversarial examples which are designed to mislead classifiers with a very small perturbation. However, the performance of black-box attacks (with…

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability

2023-08-05 · ICCV 2023 1 · Bin Chen, Jia-Li Yin, Shukai Chen, Bo-Hao Chen 외

While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gaine…

Adversarial Attack