LawBreaker: An Approach for Specifying Traffic Laws and Fuzzing Autonomous Vehicles
Autonomous driving systems (ADSs) must be tested thoroughly before they can be deployed in autonomous vehicles. High-fidelity simulators allow them to be tested against diverse scenarios, including those that are difficult to recreate in real-world testing grounds. While previous approaches have shown that test cases can be generated automatically, they tend to focus on weak oracles (e.g. reaching the destination without collisions) without assessing whether the journey itself was undertaken safely and satisfied the law. In this work, we propose LawBreaker, an automated framework for testing ADSs against real-world traffic laws, which is designed to be compatible with different scenario description languages. LawBreaker provides a rich driver-oriented specification language for describing traffic laws, and a fuzzing engine that searches for different ways of violating them by maximising specification coverage. To evaluate our approach, we implemented it for Apollo+LGSVL and specified the traffic laws of China. LawBreaker was able to find 14 violations of these laws, including 173 test cases that caused accidents.
Tue 11 OctDisplayed time zone: Eastern Time (US & Canada) change
10:30 - 12:30 | Technical Session 3 - Fuzzing IResearch Papers / Tool Demonstrations / NIER Track at Banquet B Chair(s): Aravind Machiry Purdue University | ||
10:30 20mResearch paper | LawBreaker: An Approach for Specifying Traffic Laws and Fuzzing Autonomous Vehicles Research Papers Yang Sun Singapore Management University, Singapore, Chris Poskitt Singapore Management University, Jun Sun Singapore Management University, Yuqi Chen ShanghaiTech University, China, Zijiang Yang Xi'an Jiaotong University and GuardStrike Inc DOI Pre-print | ||
10:50 20mResearch paper | Fuzzle: Making a Puzzle for FuzzersACM SIGSOFT Distinguished Paper Award Research Papers | ||
11:10 10mDemonstration | ADEPT: A Testing Platform for Simulated Autonomous DrivingVirtual Tool Demonstrations Sen Wang Nanjing University, Zhuheng Sheng Nanjing University, Jingwei Xu , Taolue Chen University of Surrey, UK, Junjun Zhu Nanjing University, Shuhui Zhang Nanjing University, Yuan Yao Nanjing University, Xiaoxing Ma Nanjing University | ||
11:20 20mResearch paper | HTFuzz: Heap Operation Sequence Sensitive FuzzingVirtual Research Papers Yuanping Yu Institute of Software, Chinese Academy of Sciences, Xiangkun Jia Institute of Software Chinese Academy of Sciences, Yuwei Liu Institute of Software, Chinese Academy of Sciences, Yanhao Wang Qi An Xin Group Corp., Qian Sang Institute of Software, Chinese Academy of Sciences, Chao Zhang Tsinghua University, Purui Su Institute of Software/CAS China | ||
11:40 20mResearch paper | Efficient Greybox Fuzzing to Detect Memory ErrorsVirtualACM SIGSOFT Distinguished Paper Award Research Papers Jinsheng Ba National University of Singapore, Gregory J. Duck National University of Singapore, Abhik Roychoudhury National University of Singapore | ||
12:00 20mResearch paper | Griffin: Grammar-Free DBMS FuzzingVirtual Research Papers Jingzhou Fu School of Software, Tsinghua University, Jie Liang School of Software, Tsinghua University, Zhiyong Wu Tsinghua University, China, Mingzhe Wang Tsinghua University, Yu Jiang Tsinghua University | ||
12:20 10mVision and Emerging Results | A Novel Coverage-gudied Greybox Fuzzing based on Power Schedule Optimization with Time ComplexityVirtual NIER Track Shengran Wang School of Computer Science and Communication Engineering, Jiangsu University, Jinfu Chen Jiangsu University, Saihua Cai School of Computer Science and Communication Engineering, Jiangsu University, Chi Zhang Jiangsu University, Haibo Chen School of Computer Science and Communication Engineering, Jiangsu University, Jingyi Chen School of Computer Science and Communication Engineering, Jiangsu University | ||