Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective
Ningfei Wang
Network and Distributed System Security (NDSS) Symposium 2025 · Day 3 · Autonomous Vehicles
In an era increasingly reliant on autonomous driving technologies, the robustness of critical perception systems like **Traffic Sign Recognition (TSR)** is paramount. This talk, presented by Ningfei Wang from UC Irvine, delves into the often-overlooked vulnerabilities of commercial TSR systems to **physical-world adversarial attacks**. While prior research has extensively explored adversarial examples against academic deep neural network models, their real-world impact on production-grade automotive systems has remained largely underexplored and, crucially, misunderstood.
AI review
Solid, original work that closes a real gap: nobody had done a multi-vehicle, real-world measurement of whether academic adversarial-patch results actually transfer to production ADAS systems. The spatial memorization discovery is genuinely novel and practically consequential — it flips the conventional wisdom on hiding vs. appearing attacks and invalidates a pile of prior evaluation methodology in one move.