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

With emerging vision-based autonomous driving (AD) systems, it becomes increasingly important to have datasets to evaluate their correct operation and identify potential security flaws. However, when collecting a large amount of data, either human experts manually label potentially hundreds of thousands of image frames or systems use machine learning algorithms to label the data, with the hope that the accuracy is good enough for the application. This can become especially problematic when tracking the context information, such as the location and velocity of surrounding objects, useful to evaluate the correctness and improve stability and robustness of the AD systems.

View More Papers

Model-Agnostic Defense for Lane Detection against Adversarial Attack

Henry Xu, An Ju, and David Wagner (UC Berkeley) Baidu Security Auto-Driving Security Award Winner ($1000 cash prize)!

Read More

CANCloak: Deceiving Two ECUs with One Frame

Li Yue, Zheming Li, Tingting Yin, and Chao Zhang (Tsinghua University)

Read More

Cross-Language Attacks

Samuel Mergendahl (MIT Lincoln Laboratory), Nathan Burow (MIT Lincoln Laboratory), Hamed Okhravi (MIT Lincoln Laboratory)

Read More

Context-Sensitive and Directional Concurrency Fuzzing for Data-Race Detection

Zu-Ming Jiang (Tsinghua University), Jia-Ju Bai (Tsinghua University), Kangjie Lu (University of Minnesota), Shi-Min Hu (Tsinghua University)

Read More