Unsupervised Anomaly Detection for Improving Adversarial Robustness of 3D Object Detection Models

Mumuxin Cai; Xupeng Wang; Ferdous Sohel; Hang Lei

doi:10.3390/electronics14020236

Back

Unsupervised Anomaly Detection for Improving Adversarial Robustness of 3D Object Detection Models

Journal article

Open access

Peer reviewed

Unsupervised Anomaly Detection for Improving Adversarial Robustness of 3D Object Detection Models

Mumuxin Cai, Xupeng Wang, Ferdous Sohel and Hang Lei

Electronics (Basel), Vol.14(2), 236

2025

DOI: https://doi.org/10.3390/electronics14020236

Files and links (1)

pdf

Published2.34 MBDownload View

CC BY V4.0, Open Access

Abstract

anomaly detection

adversarial robustness

3D object detection

security of autonomous driving

Three-dimensional object detection based on deep neural networks (DNNs) is widely used in safety-related applications, such as autonomous driving. However, existing research has shown that 3D object detection models are vulnerable to adversarial attacks. Hence, the improvement on the robustness of deep 3D detection models under adversarial attacks is investigated in this work. A deep autoencoder-based anomaly detection method is proposed, which has a strong ability to detect elaborate adversarial samples in an unsupervised way. The proposed anomaly detection method operates on a given Light Detection and Ranging (LiDAR) scene in its Bird’s Eye View (BEV) image and reconstructs the scene through an autoencoder. To improve the performance of the autoencoder, an augmented memory module with typical normal patterns recorded is introduced. It is designed to help the model to amplify the reconstruction errors of malicious samples with normal samples negligibly affected. Experiments on several public datasets show that the proposed anomaly detection method achieves an AUC of 0.8 under adversarial attacks and improves the robustness of 3D object detection.

Details

Title: Unsupervised Anomaly Detection for Improving Adversarial Robustness of 3D Object Detection Models
Authors/Creators: Mumuxin Cai - University of Electronic Science and Technology of China
Xupeng Wang - University of Electronic Science and Technology of China
Ferdous Sohel - Murdoch University, Centre for Crop and Food Innovation
Hang Lei - University of Electronic Science and Technology of China
Publication Details: Electronics (Basel), Vol.14(2), 236
Publisher: MDPI; BASEL
Number of pages: 18
Grant note: National Natural Science Foundation of ChinaSichuan Provincial Research Plan Project: 2022ZDZX0005, 24ZDZX0001, 24ZDZX0002
This work was supported by the National Natural Science Foundation of China (No. 62072076), Sichuan Provincial Research Plan Project (No. 2022ZDZX0005, No. 24ZDZX0001, No. 24ZDZX0002).
Identifiers: 991005738245207891
Murdoch Affiliation: School of Information Technology
Language: English
Resource Type: Journal article

Metrics

2 File views/ downloads

20 Record Views

5 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 4 Electrical Engineering, Electronics & Computer Science; 4.17 Computer Vision & Graphics; 4.17.2798 Stereo Depth Estimation
Web Of Science research areas: Computer Science, Information Systems; Engineering, Electrical & Electronic; Physics, Applied
ESI research areas: Engineering