Invisible Backdoor Attacks on Deep Neural Networks Via Steganography and Regularization

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this article, we create covert and scatter...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on dependable and secure computing 2021-09, Vol.18 (5), p.2088-2105
Main Authors: Li, Shaofeng, Xue, Minhui, Zhao, Benjamin Zi Hao, Zhu, Haojin, Zhang, Xinpeng
Format: Article
Language:English
Subjects:
Artificial neural networks
Backdoor attacks
Data models
deep neural networks
Image color analysis
Inspection
Machine learning
Malware
Neural networks
Perturbation methods
Regularization
Similarity
Steganography
Training
Visibility
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this article, we create covert and scattered triggers for backdoor attacks, invisible backdoors , where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steganography. The second approach of a trojan attack uses two types of additional regularization terms to generate the triggers with irregular shape and size. We use the Attack Success Rate and Functionality to measure the performance of our attacks. We introduce two novel definitions of invisibility for human perception; one is conceptualized by the Perceptual Adversarial Similarity Score (PASS) and the other is Learned Perceptual Image Patch Similarity (LPIPS). We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators. We finally argue that the proposed invisible backdoor attacks can effectively thwart the state-of-the-art trojan backdoor detection approaches.
ISSN:1545-5971
1941-0018
DOI:10.1109/TDSC.2020.3021407