Learning-Guided Network Fuzzing for Testing Cyber-Physical System Defences
The threat of attack faced by cyber-physical systems (CPSs), especially when they play a critical role in automating public infrastructure, has motivated research into a wide variety of attack defence mechanisms. Assessing their effectiveness is challenging, however, as realistic sets of attacks to test them against are not always available. In this paper, we propose smart fuzzing, an automated, machine learning guided technique for systematically finding ‘test suites’ of CPS network attacks, without requiring any expertise in the system’s control programs or physical processes. Our approach uses predictive machine learning models and metaheuristic search algorithms to guide the fuzzing of actuators so as to drive the CPS into different unsafe physical states. We demonstrate the efficacy of smart fuzzing by implementing it for two real-world CPS testbeds—a water purification plant and a water distribution system—finding attacks that drive them into 27 different unsafe states involving water flow, pressure, and tank levels, including six that were not covered by an established attack benchmark. Finally, we use our approach to test the effectiveness of an invariant-based defence system for the water treatment plant, finding two attacks that were not detected by its physical invariant checks, highlighting a potential weakness that could be exploited in certain conditions.
Slides (2019-11-ASE-for-web.pdf) | 5.99MiB |
Thu 14 Nov
16:00 - 17:40: Papers - Emerging Domains at Cortez 1 Chair(s): Joshua GarciaUniversity of California, Irvine | ||||||||||||||||||||||||||||||||||||||||||
16:00 - 16:20 Talk | Improving the Decision-Making Process of Self-Adaptive Systems by Accounting for Tactic Volatility Jeffrey PalmerinoRochester Institute of Technology, Qi YuRochester Institute of Technology, Travis Desell University of North Dakota, Daniel KrutzRochester Institute of Technology Pre-print | |||||||||||||||||||||||||||||||||||||||||
16:20 - 16:40 Talk | Learning-Guided Network Fuzzing for Testing Cyber-Physical System Defences Yuqi ChenSingapore University of Technology and Design, Singapore, Chris PoskittSingapore University of Technology and Design, Jun SunSingapore Management University, Singapore, Sridhar AdepuSingapore University of Technology and Design, Singapore, Fan ZhangZhejiang University, Zhejiang Lab, and Alibaba-Zhejiang University Joint Institute of Frontier Technologies, China Pre-print File Attached | |||||||||||||||||||||||||||||||||||||||||
16:40 - 17:00 Talk | Uncertainty-wise Test Case Generation and Minimization for Cyber-Physical Systems Man ZhangKristiania University, Shaukat AliSimula Research Lab, Tao YueNanjing University of Aeronautics and Astronautics & Simula Research Laboratory Link to publication | |||||||||||||||||||||||||||||||||||||||||
17:00 - 17:20 Talk | Finding Trends in Software Research George MathewDepartment of Computer Science, North Carolina State University, Amritanshu AgrawalWayfair, Tim MenziesNorth Carolina State University Link to publication | |||||||||||||||||||||||||||||||||||||||||
17:20 - 17:30 Demonstration | XRaSE: Towards Virtually Tangible Software using Augmented Reality Rohit MehraAccenture Labs, India, Vibhu Saujanya SharmaAccenture Labs, Vikrant KaulgudAccenture Labs, India, Sanjay PodderAccenture | |||||||||||||||||||||||||||||||||||||||||
17:30 - 17:40 Demonstration | MuSC: A Tool for Mutation Testing of Ethereum Smart Contract Zixin LiNanjing University, Haoran WuState Key Laboratory for Novel Software Technology, Nanjing University, Jiehui XuNanjing University, Xingya WangState Key Laboratory for Novel Software Technology, Nanjing University, Lingming ZhangThe University of Texas at Dallas, Zhenyu ChenNanjing University |