52 citations · 63 across the 4 of their papers we have counts for
4 papers · 1 filter
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising
Zikang Xiong, Joe Eappen, He Zhu +1
Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as p…
Robustness to Adversarial Attacks in Learning-Enabled Controllers
Zikang Xiong, Joe Eappen, He Zhu +1
Learning-enabled controllers used in cyber-physical systems (CPS) are known to be susceptible to adversarial attacks. Such attacks manifest as perturbations to the states generated…
An Inductive Synthesis Framework for Verifiable Reinforcement Learning
He Zhu, Zikang Xiong, Stephen Magill +1
Despite the tremendous advances that have been made in the last decade on developing useful machine-learning applications, their wider adoption has been hindered by the lack of str…
ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks
Xuankang Lin, He Zhu, Roopsha Samanta +1
Artificial Neural Networks (ANNs) have demonstrated remarkable utility in various challenging machine learning applications. While formally verified properties of their behaviors a…