no code implementations • 27 Mar 2024 • Zikang Xiong, Suresh Jagannathan
In this paper, we propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners.
no code implementations • 2 Mar 2023 • Zikang Xiong, Daniel Lawson, Joe Eappen, Ahmed H. Qureshi, Suresh Jagannathan
Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics.
Hierarchical Reinforcement Learning reinforcement-learning +2
1 code implementation • 28 Jun 2022 • Joe Eappen, Suresh Jagannathan
While notable progress has been made in specifying and learning objectives for general cyber-physical systems, applying these methods to distributed multi-agent systems still pose significant challenges.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 14 Jun 2022 • Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
We focus our attention on well-trained deterministic and stochastic neural network policies in the context of continuous control benchmarks subject to four well-studied observation space adversarial attacks.
1 code implementation • 2 Mar 2022 • Zikang Xiong, Joe Eappen, Ahmed H. Qureshi, Suresh Jagannathan
Model-free Deep Reinforcement Learning (DRL) controllers have demonstrated promising results on various challenging non-linear control tasks.
no code implementations • 20 Apr 2021 • Zikang Xiong, Suresh Jagannathan
There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems.
no code implementations • 9 Mar 2021 • Kia Rahmani, Kartik Nagar, Benjamin Delaware, Suresh Jagannathan
Serializability is a well-understood concurrency control mechanism that eases reasoning about highly-concurrent database programs.
Programming Languages
no code implementations • 11 Jun 2020 • Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations.
1 code implementation • 17 Jul 2019 • Xuankang Lin, He Zhu, Roopsha Samanta, Suresh Jagannathan
Our key insight is that we can integrate an optimization-based abstraction refinement loop into the learning process and operate over dynamically constructed partitions of the input space that considers accuracy and safety objectives synergistically.
no code implementations • 16 Jul 2019 • He Zhu, Zikang Xiong, Stephen Magill, Suresh Jagannathan
Rather than enforcing safety by examining and altering the structure of a complex neural network implementation, our technique uses blackbox methods to synthesizes deterministic programs, simpler, more interpretable, approximations of the network that can nonetheless guarantee desired safety properties are preserved, even when the network is deployed in unanticipated or previously unobserved environments.