Work

Demo: Invisible Adversarial Stripes against Traffic Sign Recognition in Autonomous Driving

Year: 2024

Type: conference-paper

Abstract: Camera-based computer vision is crucial for autonomous vehicle perception. We demonstrate GhostStripe [5], an attack system that uses light-emitting diodes and exploits the camera's rolling shutter effect to generate adversarial stripes that are invisible to humans while misleading traffic sign recognition. To maintain stable attack effectiveness, GhostStripe controls the timing of the modulated light emission, adapting to both the camera's framing operation and the movement of the victim vehicle. Evaluated on real testbeds, GhostStripe can stably spoof traffic sign recognition results for up to 97% of frames to a wrong class when the victim vehicle passes the road section.

Source: ACM Conference on Embedded Networked Sensor Systems (SenSys)

DOI: 10.1145/3666025.3699401

Authors: Dongfang Guo, Yuting Wu, Yimin Dai, Pengfei Zhou, Xin Lou, Rui Tan

Institutions: Nanyang Technological University, University of Pittsburgh, Singapore Institute of Technology

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Research Foundation, National Research Foundation Singapore

OpenAlex ID: W4404034664

FWCI:

Cites: 3

Cited by:

Related to: 10