L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target
Taifeng Liu
Network and Distributed System Security (NDSS) Symposium 2025 · Day 3 · Autonomous Vehicles
The proliferation of AI-powered autonomous systems, particularly in self-driving vehicles, has brought unprecedented levels of automation and safety enhancements to transportation. Central to these advancements are sophisticated vision-based recognition systems, enabling vehicles to accurately perceive and interpret their surroundings, from identifying traffic signs to detecting obstacles. However, despite their high accuracy, these systems harbor surprising fragilities, a vulnerability that the research presented in "L-HAWK: A Controllable Physical Adversarial Patch Against a Long-Distance Target" starkly illuminates. This talk, delivered by Taifeng Liu from Peking University, introduces a novel and highly concerning form of adversarial attack that can manipulate autonomous vehicles from a distance, with a degree of control previously unachieved in the field.
AI review
L-HAWK is genuine offensive research with a clear novel contribution: laser-triggered, selective adversarial patch activation at meaningful real-world distances. The asynchronous optimization and progressive sampling solutions to the controllability and lens-scattering problems are technically credible, and the experimental numbers — particularly the end-to-end AV eval at 80%+ — put this well above the usual 'we printed a patch on a stop sign' adversarial ML paper.