Vulnerability Exploration of Safe Reinforcement Learning in Cyber-Physical Systems via STL Mining
Open Access
- 11 May 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Abstract
No abstract availableFunding Information
- National Science Foundation (CNS-2333980)
- National Science Foundation (CNS-2442914)
This publication has 24 references indexed in Scilit:
- Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective2025
- Improve Robustness of Safe Reinforcement Learning Against Adversarial Attacks2024
- Mining signal temporal logic specifications for hybrid systems2024
- Vulnerability Analysis for Safe Reinforcement Learning in Cyber-Physical Systems2024
- Mining Specification Parameters for Multi-class Classification2023
- Mining Environment Assumptions for Cyber-Physical System Models2020
- TeLEx: Passive STL Learning Using Only Positive Examples2017
- MuJoCo: A physics engine for model-based control2012
- Robustness of Temporal Logic Specifications2006
- Monitoring Temporal Properties of Continuous Signals2004