Backdoor Attack with Sparse and Invisible Trigger

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Yinghua, Li, Yiming, Gong, Xueluan, Li, Zhifeng, Xia, Shu-Tao, Wang, Qian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911906779889664
author Gao, Yinghua
Li, Yiming
Gong, Xueluan
Li, Zhifeng
Xia, Shu-Tao
Wang, Qian
author_facet Gao, Yinghua
Li, Yiming
Gong, Xueluan
Li, Zhifeng
Xia, Shu-Tao
Wang, Qian
contents Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available at \url{https://github.com/YinghuaGao/SIBA}.
format Preprint
id arxiv_https___arxiv_org_abs_2306_06209
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Backdoor Attack with Sparse and Invisible Trigger
Gao, Yinghua
Li, Yiming
Gong, Xueluan
Li, Zhifeng
Xia, Shu-Tao
Wang, Qian
Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available at \url{https://github.com/YinghuaGao/SIBA}.
title Backdoor Attack with Sparse and Invisible Trigger
topic Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2306.06209