Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

J Shi, Z Yang, J He, B Xu, D Kim, DG Han… - ACM Transactions on …, 2024 - dl.acm.org
Given the increasing adoption of modern AI-enabled control systems, ensuring their safety
and reliability has become a critical task in software testing. One prevalent approach to …

Policy Testing with MDPFuzz (Replicability Study)

Q Mazouni, H Spieker, A Gotlieb, M Acher - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
In recent years, following tremendous achievements in Reinforcement Learning, a great
deal of interest has been devoted to ML models for sequential decision-making. Together …

Exploration-Driven Reinforcement Learning for Avionic System Fault Detection (Experience Paper)

PA Le Tolguenec, E Rachelson, Y Besse… - Proceedings of the 33rd …, 2024 - dl.acm.org
Critical software systems require stringent testing to identify possible failure cases, which
can be difficult to find using manual testing. In this study, we report our industrial experience …

Synthesizing Efficient and Permissive Programmatic Runtime Shields for Neural Policies

J Shi, J He, Z Yang, Đ Žikelić, D Lo - arxiv preprint arxiv:2410.05641, 2024 - arxiv.org
With the increasing use of neural policies in control systems, ensuring their safety and
reliability has become a critical software engineering task. One prevalent approach to …

Safety and Reliability of DRL Agents Through Testing and Safety Monitoring

A Zolfagharian - 2024 - ruor.uottawa.ca
Abstract Deep Reinforcement Learning (DRL) agents have shown significant promise
across various domains, including autonomous driving, healthcare, and robotics. However …