paper-with-me

Papers

LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks

2024-12-05 · Yongjie Xu, Guangke Chen, Fu Song, Yuqi Chen

Backdoor attacks embed hidden associations between triggers and targets in deep neural networks (DNNs), causing them to predict the target when a trigger is present while maintaining normal behavior otherwise. Physical backdoor attacks, which use physical objects as triggers, are feasible but lack remote control, temporal stealthiness, flexibility, and mobility. To overcome these limitations, in this work, we propose a new type of backdoor triggers utilizing lasers that feature long-distance transmission and instant-imaging properties. Based on the laser-based backdoor triggers, we present a physical backdoor attack, called LaserGuider, which possesses remote control ability and achieves high temporal stealthiness, flexibility, and mobility. We also introduce a systematic approach to optimize laser parameters for improving attack effectiveness. Our evaluation on traffic sign recognition DNNs, critical in autonomous vehicles, demonstrates that LaserGuider with three different laser-based triggers achieves over 90% attack success rate with negligible impact on normal inputs. Additionally, we release LaserMark, the first dataset of real world traffic signs stamped with physical laser spots, to support further research in backdoor attacks and defenses.

📄 PDF Abstract BibTeX arXiv:2412.03993

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous VehiclesBackdoor AttackTraffic Sign Recognition

Similar Papers 제목 키워드 기반

Backdoor Attacks Against Deep Learning Systems in the Physical World

2020-06-25 · CVPR 2021 1 · Emily Wenger, Josephine Passananti, Arjun Bhagoji, Yuanshun Yao 외

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses…

Deep LearningTransfer Learning

Robust Backdoor Attacks against Deep Neural Networks in Real Physical World

2021-04-15 · Mingfu Xue, Can He, Shichang Sun, Jian Wang 외

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, …

Backdoor AttackFace Recognition

Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks

2020-10-07 · Ahmed Salem, Michael Backes, Yang Zhang

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usuall…

Backdoor Attack

TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation

2024-11-18 · Xianlong Wang, Hewen Pan, Hangtao Zhang, Minghui Li 외

Robotic manipulation in the physical world is increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recent…

Backdoor AttackDecision MakingLanguage ModelingLanguage Modelling

BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World

2025-05-22 · Ji Guo, Long Zhou, Zhijin Wang, Jiaming He 외

In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored…

Autonomous DrivingBackdoor AttackDepth CompletionDepth Estimation+3