PhyScout: Detecting Sensor Spoofing Attacks via Spatio-temporal Consistency
Open Access
- 2 December 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1879-1893
Abstract
Existing defense approaches against sensor spoofing attacks suffer from the limitations of limited specific attack types, requiring GPU computation, exhibiting considerable detection latency and struggling with the interpretability of corner cases. We developed PhyScout, a holistic sensor spoofing defense framework to overcome the above limitations. Our framework capitalizes on the observation that human drivers can rapidly and accurately identify spoofing attacks by performing spatio-temporal consistency checks of their environment. We commence by defining the generalized conflicts that different sensor spoofing attacks produce regarding the spatio-temporal consistency. These conflicts are subsequently unified and formalized through a least squares problem approach. This process is modeled using image-based feature point extraction and matching techniques, followed by the design of a risk identification method for each conflict. We evaluate PhyScout across various environments, including simulators, datasets, and real-world scenarios. Compared to existing defense solutions, PhyScout offers rapid identification of sensor attacks (within 100ms) with low performance overhead (CPU-based), and conflict visualization. It demonstrates a fresh paradigm in autonomous vehicle security and presents new avenues for future research in robust and efficient defense mechanisms against sensor spoofing attacks. More video demos are at our anonymous website https://sites.google.com/view/physcout.Keywords
Funding Information
- NTU-DESAY SV Research Program (2018-0980)
- National Research Foundation, Singapore and DSO National Laboratories (AISG2-GC-2023-008)
This publication has 41 references indexed in Scilit:
- Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches2022
- Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World2021
- Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink2021
- Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors2020
- PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving2020
- Universal Physical Camouflage Attacks on Object Detectors2020
- A Friendly and Low-Cost Technique for Capturing Non-Cooperative Civilian Unmanned Aerial VehiclesIEEE Network, 2018
- DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic ScenesIEEE Robotics and Automation Letters, 2018
- Illusion and Dazzle: Adversarial Optical Channel Exploits Against Lidars for Automotive Applications2017
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004