paper-with-me

Papers

DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain

2024-06-05 · Jun Liu, Jiantao Zhou, Jiandian Zeng, Jinyu Tian, Zheng Li

This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (\textbf{ASR}) and good generalizability. We design a novel attack method based on a hierarchical DIsentangled Feature space, called \textbf{DifAttack++}, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack++ firstly disentangles an image's latent feature into an Adversarial Feature (\textbf{AF}) and a Visual Feature (\textbf{VF}) via an autoencoder equipped with our specially designed Hierarchical Decouple-Fusion (\textbf{HDF}) module, where the AF dominates the adversarial capability of an image, while the VF largely determines its visual appearance. We train such two autoencoders for the clean and adversarial image domains (i.e., cross-domain) respectively to achieve image reconstructions and feature disentanglement, by using pairs of clean images and their Adversarial Examples (\textbf{AE}s) generated from available surrogate models via white-box attack methods. Eventually, in the black-box attack stage, DifAttack++ iteratively optimizes the AF according to the query feedback from the victim model until a successful AE is generated, while keeping the VF unaltered. Extensive experimental results demonstrate that our DifAttack++ leads to superior ASR and query efficiency than state-of-the-art methods, meanwhile exhibiting much better visual quality of AEs. The code is available at https://github.com/csjunjun/DifAttack.git.

📄 PDF Abstract BibTeX arXiv:2406.03017

Code (1)

csjunjun/difattack 공식 구현 pytorch

Tasks

Adversarial AttackDisentanglement

Methods 이 논문이 사용한 방법론

AE An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation…

Similar Papers 제목 키워드 기반

DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space

2023-09-26 · Liu jun, Zhou Jiantao, Zeng Jiandian, Jinyu Tian

This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called Di…

Disentanglement

Improving Query Efficiency of Black-box Adversarial Attack

2020-09-24 · ECCV 2020 8 · Yang Bai, Yuyuan Zeng, Yong Jiang, Yisen Wang 외

Deep neural networks (DNNs) have demonstrated excellent performance on various tasks, however they are under the risk of adversarial examples that can be easily generated when the target model is accessible to an attacke…

Adversarial Attack

Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks

2020-06-24 · Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang 외

Deep learning systems are known to be vulnerable to adversarial examples. In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the ne…

image-classificationImage Classificationtext-classificationText Classification

EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks

2021-07-12 · Andrei Ilie, Marius Popescu, Alin Stefanescu

Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency a…

Adversarial Attack

Black-box Adversarial Attacks with Bayesian Optimization

2019-09-30 · Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) …

Bayesian Optimization