Backdoor Attack With Sparse and Invisible Trigger
- 10 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 6364-6376
Abstract
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 https://github.com/YinghuaGao/SIBA.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U20A20178, 62171248, U20B2049, U21B2018)
- Shenzhen Science and Technology Program (JCYJ20220818101012025)
- Peng Cheng National Laboratory (PCNL) KEY Project (PCL2023AS6-1)
This publication has 44 references indexed in Scilit:
- Backdoor Attacks Against Deep Learning Systems in the Physical World2021
- Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-Based Approach2020
- Compressing Convolutional Neural Networks via Factorized Convolutional Filters2019
- Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition2019
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- Wild patterns: Ten years after the rise of adversarial machine learningPattern Recognition, 2018
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Deep Residual Learning for Image Recognition2016
- Iterative hard thresholding methods for $l_0$ l 0 regularized convex cone programmingMathematical Programming, 2013