Currently, there is a substantial push towards autonomous vehicles in the market. However, fully autonomous vehicles, using extensive fault-tolerance e.g., in x-by-wire functions, are still not quite safe from an accidental faults perspective. Furthermore, they present an even greater threat surface to combined accidental and malicious faults. This pitfall has been very slowly recognized by car makers. The consequences of such accidents or attacks are likely to be severe, life-threatening included. This talk will discuss this threat surface in an analysis including the whole ecosystem. Then I will discuss how the incorporation of resilience techniques can bring autonomous vehicle ecosystems to the desired level of safety and security, in an incremental, dynamic, and adaptive way. Finally, we will discuss quite important misconceptions and pitfalls originating from the use of inappropriate AI/ML techniques in autonomous vehicles, which have been the cause of serious accidents. We suggest paths to address this serious problem.
Paulo Esteves-Veríssimo is a Professor at KAUST University (KSA) and Director of its Resilient Computing and Cybersecurity Center (https://rc3.kaust.edu.sa/), and research fellow of SnT at the University of Luxembourg. He was a member of the Sci&Tech. Comm. of ECSO EU Cyber Security Org., Chair of IFIP WG 10.4 on Dependable Comp. and F/T, and vice-Chair of the Steer. Comm. of the DSN conference. He is Fellow of IEEE and of ACM, and former associate editor of IEEE Trans. on Computers (TC) and Trans. on Emerging Topics in Computing (TETC), author of over 200 peer-refereed publications and co-author of 5 books. He is currently interested in resilient computing, in areas like: SDN-based infrastructures; autonomous vehicles; distributed control systems; digital health and genomics; or blockchain and cryptocurrencies.