Christopher DiPalma, Ningfei Wang, Takami Sato, and Qi Alfred Chen (UC Irvine)

Robust perception is crucial for autonomous vehicle security. In this work, we design a practical adversarial patch attack against camera-based obstacle detection. We identify that the back of a box truck is an effective attack vector. We also improve attack robustness by considering a variety of input frames associated with the attack scenario. This demo includes videos that show our attack can cause end-to-end consequences on a representative autonomous driving system in a simulator.

View More Papers

Demo #1: Security of Multi-Sensor Fusion based Perception in...

Yulong Cao (University of Michigan), Ningfei Wang (UC, Irvine), Chaowei Xiao (Arizona State University), Dawei Yang (University of Michigan), Jin Fang (Baidu Research), Ruigang Yang (University of Michigan), Qi Alfred Chen (UC, Irvine), Mingyan Liu (University of Michigan) and Bo Li (University of Illinois at Urbana-Champaign)

Read More

WATSON: Abstracting Behaviors from Audit Logs via Aggregation of...

Jun Zeng (National University of Singapore), Zheng Leong Chua (Independent Researcher), Yinfang Chen (National University of Singapore), Kaihang Ji (National University of Singapore), Zhenkai Liang (National University of Singapore), Jian Mao (Beihang University)

Read More

My Past Dictates my Present: Relevance, Exposure, and Influence...

Shujaat Mirza, Christina Pöpper (New York University)

Read More

Effects of Precise and Imprecise Value-Set Analysis (VSA) Information...

Laura Matzen, Michelle A Leger, Geoffrey Reedy (Sandia National Laboratories)

Read More