Pritam Dash (University of British Columbia) and Karthik Pattabiraman (University of British Columbia)

Robotic Vehicles (RV) rely extensively on sensor inputs to operate autonomously. Physical attacks such as sensor tampering and spoofing feed erroneous sensor measurements to deviate RVs from their course and result in mission failures. We present PID-Piper , a novel framework for automatically recovering RVs from physical attacks. We use machine learning (ML) to design an attack resilient FeedForward Controller (FFC), which runs in tandem with the RV’s primary controller and monitors it. Under attacks, the FFC takes over from the RV’s primary controller to recover the RV, and allows the RV to complete its mission successfully. Our evaluation on 6 RV systems including 3 real RVs shows that PID-Piper allows RVs to complete their missions successfully despite attacks in 83% of the cases.

View More Papers

MIRROR: Model Inversion for Deep LearningNetwork with High Fidelity

Shengwei An (Purdue University), Guanhong Tao (Purdue University), Qiuling Xu (Purdue University), Yingqi Liu (Purdue University), Guangyu Shen (Purdue University);...

Read More

(Short) Fooling Perception via Location: A Case of Region-of-Interest...

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

Read More

DRIVETRUTH: Automated Autonomous Driving Dataset Generation for Security Applications

Raymond Muller (Purdue University), Yanmao Man (University of Arizona), Z. Berkay Celik (Purdue University), Ming Li (University of Arizona) and...

Read More

WeepingCAN: A Stealthy CAN Bus-off Attack

Gedare Bloom (University of Colorado Colorado Springs) Best Paper Award Winner ($300 cash prize)!

Read More