“We will study data corruption by attackers who have obtained access to the system’s sensors and adversarial examples that can be implemented by introducing tiny changes to the system’s environment,” says Lou. “We will design attack detection and thwarting approaches and develop their efficient implementations suitable for embedded hardware accelerators.”
Lou says his team will also construct a testbed to capture representative cyber components of autonomous cyber-physical systems. Doing so will facilitate the design, evaluation, and demonstration of the threats and countermeasures. Demonstrating these vulnerabilities will reinforce industry awareness of the criticality of these studied threats.
“We view safety as a basic requirement, rather than a profitable feature,” says Lou. “The technological advances in this project will also promote the development of the smart nation concept and strengthen Singapore’s leadership in having the most advanced and trustworthy computing technologies in the world.”
Lou hopes that the advances made in this research will benefit both academia and industry. The breakthroughs made on both internal or external attacks will be documented in technical disclosures and top-tier publications. When the project is finished, the team will deliver a testbed capable of demonstrating the algorithms designed by the team.
“Many high-tech companies like Google, Apple, and Tesla are developing their own autonomous vehicles and expecting them to be on the road in near future,” says Lou. “UAVs have also been used for other critical missions like space exploration and military defense. With the increasing applications of autonomous cyber-physical systems, the requirement of security and safety assurance becomes prominent.”