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

A First Look at Scams on YouTube

Elijah Bouma-Sims, Bradley Reaves (North Carolina State University)

Read More

All the Numbers are US: Large-scale Abuse of Contact...

Christoph Hagen (University of Würzburg), Christian Weinert (TU Darmstadt), Christoph Sendner (University of Würzburg), Alexandra Dmitrienko (University of Würzburg), Thomas Schneider (TU Darmstadt)

Read More

Generation of CAN-based Wheel Lockup Attacks on the Dynamics...

Alireza Mohammadi (University of Michigan-Dearborn), Hafiz Malik (University of Michigan-Dearborn) and Masoud Abbaszadeh (GE Global Research)

Read More

Demo #4: Attacking Tesla Model X’s Autopilot Using Compromised...

Ben Nassi (Ben-Gurion University of the Negev), Yisroel Mirsky (Ben-Gurion University of the Negev, Georgia Tech), Dudi Nassi, Raz Ben Netanel (Ben-Gurion University of the Negev), Oleg Drokin (Independent Researcher), and Yuval Elovici (Ben-Gurion University of the Negev) Best Demo Award Winner ($300 cash prize)!

Read More