Camouflage Backdoor Attack against Pedestrian Detection
-
Published:2023-11-28
Issue:23
Volume:13
Page:12752
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Wu Yalun1ORCID, Gu Yanfeng1, Chen Yuanwan1, Cui Xiaoshu1, Li Qiong1, Xiang Yingxiao2, Tong Endong1, Li Jianhua3, Han Zhen1, Liu Jiqiang1ORCID
Affiliation:
1. Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing 100044, China 2. Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100085, China 3. Zhongguancun Smart City Co., Ltd., Beijing 100081, China
Abstract
Pedestrian detection models in autonomous driving systems heavily rely on deep neural networks (DNNs) to perceive their surroundings. Recent research has unveiled the vulnerability of DNNs to backdoor attacks, in which malicious actors manipulate the system by embedding specific triggers within the training data. In this paper, we propose a tailored camouflaged backdoor attack method designed for pedestrian detection in autonomous driving systems. Our approach begins with the construction of a set of trigger-embedded images. Subsequently, we employ an image scaling function to seamlessly integrate these trigger-embedded images into the original benign images, thereby creating potentially poisoned training images. Importantly, these potentially poisoned images exhibit minimal discernible differences from the original benign images and are virtually imperceptible to the human eye. We then strategically activate these concealed backdoors in specific scenarios, causing the pedestrian detection models to make incorrect judgments. Our study demonstrates that once our attack successfully embeds the backdoor into the target model, it can deceive the model into failing to detect any pedestrians marked with our trigger patterns. Extensive evaluations conducted on a publicly available pedestrian detection dataset confirm the effectiveness and stealthiness of our camouflaged backdoor attacks.
Funder
Fundamental Research Funds for the Central Universities National Natural Science Foundation of China ‘Top the List and Assume Leadership’ project in Shijiazhuang
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference35 articles.
1. Deep learning-based autonomous driving systems: A survey of attacks and defenses;Deng;IEEE Trans. Ind. Inform.,2021 2. Bogdoll, D., Nitsche, M., and Zöllner, J.M. (2022, January 18–24). Anomaly detection in autonomous driving: A survey. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA. 3. Autonomous driving security: State of the art and challenges;Gao;IEEE Internet Things J.,2021 4. Chi, C., Zhang, S., Xing, J., Lei, Z., Li, S.Z., and Zou, X. (2020, January 7–12). Pedhunter: Occlusion robust pedestrian detector in crowded scenes. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA. 5. Deep neural network based vehicle and pedestrian detection for autonomous driving: A survey;Chen;IEEE Trans. Intell. Transp. Syst.,2021
|
|