Ziwen Wan (University of California, Irvine), Junjie Shen (University of California, Irvine), Jalen Chuang (University of California, Irvine), Xin Xia (The University of California, Los Angeles), Joshua Garcia (University of California, Irvine), Jiaqi Ma (The University of California, Los Angeles), Qi Alfred Chen (University of California, Irvine)

In high-level Autonomous Driving (AD) systems, behavioral planning is in charge of making high-level driving decisions such as cruising and stopping, and thus highly security-critical. In this work, we perform the first systematic study of semantic security vulnerabilities specific to overly-conservative AD behavioral planning behaviors, i.e., those that can cause failed or significantly-degraded mission performance, which can be critical for AD services such as robo-taxi/delivery. We call them semantic Denial-of-Service (DoS) vulnerabilities, which we envision to be most generally exposed in practical AD systems due to the tendency for conservativeness to avoid safety incidents. To achieve high practicality and realism, we assume that the attacker can only introduce seemingly-benign external physical objects to the driving environment, e.g., off-road dumped cardboard boxes.

To systematically discover such vulnerabilities, we design PlanFuzz, a novel dynamic testing approach that addresses various problem-specific design challenges. Specifically, we propose and identify planning invariants as novel testing oracles, and design new input generation to systematically enforce problem-specific constraints for attacker-introduced physical objects. We also design a novel behavioral planning vulnerability distance metric to effectively guide the discovery. We evaluate PlanFuzz on 3 planning implementations from practical open-source AD systems, and find that it can effectively discover 9 previously-unknown semantic DoS vulnerabilities without false positives. We find all our new designs necessary, as without each design, statistically significant performance drops are generally observed. We further perform exploitation case studies using simulation and real-vehicle traces. We discuss root causes and potential fixes.

View More Papers

PASS: A System-Driven Evaluation Platform for Autonomous Driving Safety...

Zhisheng Hu (Baidu Security), Junjie Shen (UC Irvine), Shengjian Guo (Baidu Security), Xinyang Zhang (Baidu Security), Zhenyu Zhong (Baidu Security), Qi Alfred Chen (UC Irvine) and Kang Li (Baidu Security)

Read More

ScriptChecker: To Tame Third-party Script Execution With Task Capabilities

Wu Luo (Peking University), Xuhua Ding (Singapore Management University), Pengfei Wu (School of Computing, National University of Singapore), Xiaolei Zhang (Peking University), Qingni Shen (Peking University), Zhonghai Wu (Peking University)

Read More

Fuzzing: A Tale of Two Cultures

Andreas Zeller (CISPA Helmholtz Center for Information Security)

Read More

DRAWN APART: A Device Identification Technique based on Remote...

Tomer Laor (Ben-Gurion Univ. of the Negev), Naif Mehanna (Univ. Lille, CNRS, Inria), Antonin Durey (Univ. Lille, CNRS, Inria), Vitaly Dyadyuk (Ben-Gurion Univ. of the Negev), Pierre Laperdrix (Univ. Lille, CNRS, Inria), Cl√©mentine Maurice (Univ. Lille, CNRS, Inria), Yossi Oren (Ben-Gurion Univ. of the Negev), Romain Rouvoy (Univ. Lille, CNRS, Inria / IUF), Walter Rudametkin…

Read More