Kanglan Tang, Junjie Shen, and Qi Alfred Chen (UC Irvine)

The perception module is the key to the security of Autonomous Driving systems. It perceives the environment through sensors to help make safe and correct driving decisions on the road. The localization module is usually considered to be independent of the perception module. However, we discover that the correctness of perception output highly depends on localization due to the widely used Region-of-Interest design adopted in perception. Leveraging this insight, we propose an ROI attack and perform a case study in the traffic light detection in Autonomous Driving systems. We evaluate the ROI attack on a production-grade Autonomous Driving system, named Baidu Apollo, under end-to-end simulation environments. We found our attack is able to make the victim a red light runner or cause denial-of-service with a 100% success rate.

View More Papers

Taking a Closer Look at the Alexa Skill Ecosystem

Christopher Lentzsch (Ruhr-Universität Bochum), Anupam Das (North Carolina State University)

Read More

Demo #7: Automated Tracking System For LiDAR Spoofing Attacks...

Yulong Cao, Jiaxiang Ma, Kevin Fu (University of Michigan), Sara Rampazzi (University of Florida), and Z. Morley Mao (University of Michigan) Best Demo Award Runner-up ($200 cash prize)!

Read More

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

Shujaat Mirza, Christina Pöpper (New York University)

Read More

Sn4ke: Practical Mutation Analysis of Tests at Binary Level

Mohsen Ahmadi (Arizona State University), Pantea Kiaei (Worcester Polytechnic Institute), Navid Emamdoost (University of Minnesota)

Read More