27 citations · 94 across the 13 of their papers we have counts for
13 papers
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
Yixuan Wang, Weichao Zhou, Jiameng Fan +6
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performances on challenging control problems. However, the potential adoption of NN con…
Byzantine Resilience at Swarm Scale: A Decentralized Blocklist Protocol from Inter-robot Accusations
Kacper Wardega, Max von Hippel, Roberto Tron +2
The Weighted-Mean Subsequence Reduced (W-MSR) algorithm, the state-of-the-art method for Byzantine-resilient design of decentralized multi-robot systems, is based on discarding out…
A Tool for Neural Network Global Robustness Certification and Training
Zhilu Wang, Yixuan Wang, Feisi Fu +4
With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and…
POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems
Chao Huang, Jiameng Fan, Zhilu Wang +6
We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs). Existing approaches that le…
DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
Jiameng Fan, Wenchao Li
Deep reinforcement learning (DRL) agents are often sensitive to visual changes that were unseen in their training environments. To address this problem, we leverage the sequential…
Runtime-Safety-Guided Policy Repair
Weichao Zhou, Ruihan Gao, BaekGyu Kim +2
We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control p…
Adversarial Training and Provable Robustness: A Tale of Two Objectives
Jiameng Fan, Wenchao Li
We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training…
Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systems
Chao Huang, Shichao Xu, Zhilu Wang +3
Control schemes for autonomous systems are often designed in a way that anticipates the worst case in any situation. At runtime, however, there could exist opportunities to leverag…
ReachNN: Reachability Analysis of Neural-Network Controlled Systems
Chao Huang, Jiameng Fan, Wenchao Li +2
Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neu…
Safety-Guided Deep Reinforcement Learning via Online Gaussian Process Estimation
Jiameng Fan, Wenchao Li
An important facet of reinforcement learning (RL) has to do with how the agent goes about exploring the environment. Traditional exploration strategies typically focus on efficienc…
TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
Panagiota Kiourti, Kacper Wardega, Susmit Jha +1
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show tha…
Safety-Aware Apprenticeship Learning
Weichao Zhou, Wenchao Li
Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and t…
ARSENAL: Automatic Requirements Specification Extraction from Natural Language
Shalini Ghosh, Daniel Elenius, Wenchao Li +3
Requirements are informal and semi-formal descriptions of the expected behavior of a complex system from the viewpoints of its stakeholders (customers, users, operators, designers,…