Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks

Thumbnail Image

Files

2212.08121.pdf (1.16 MB)

Links to Files

https://arxiv.org/abs/2212.08121

Permanent Link

https://doi.org/10.48550/arXiv.2212.08121
 http://hdl.handle.net/11603/26599

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

2022-12-15

Type of Work

journal articles
preprints
Text

Department

Program

Citation of Original Publication

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution 4.0 International (CC BY 4.0)

Subjects

Abstract

The increasing importance of both deep neural networks (DNNs) and cloud services for training them means that bad actors have more incentive and opportunity to insert backdoors to alter the behavior of trained models. In this paper, we introduce a novel method for backdoor detection that extracts features from pre-trained DNN’s weights using independent vector analysis (IVA) followed by a machine learning classifier. In comparison to other detection techniques, this has a number of benefits, such as not requiring any training data, being applicable across domains, operating with a wide range of network architectures, not assuming the nature of the triggers used to change network behavior, and being highly scalable. We discuss the detection pipeline, and then demonstrate the results on two computer vision datasets regarding image classification and object detection. Our method outperforms the competing algorithms in terms of efficiency and is more accurate, helping to ensure the safe application of deep learning and AI.