215 citations · 275 across the 30 of their papers we have counts for
38 papers
Robust Reinforcement Learning through Efficient Adversarial Herding
Juncheng Dong, Hao-Lun Hsu, Qitong Gao +2
Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe…
Treatment Effects in Extreme Regimes
Ahmed Aloui, Ali Hasan, Yuting Ng +2
Understanding treatment effects in extreme regimes is important for characterizing risks associated with different interventions. This is hindered by the unavailability of counterf…
High Dimensional Geometry and Limitations in System Identification
Muhammad Abdullah Naeem, Miroslav Pajic
We study the problem of identification of linear dynamical system from a single trajectory, via excitations of isotropic Gaussian. In stark contrast with previously reported result…
A Modular Platform For Collaborative, Distributed Sensor Fusion
R. Spencer Hallyburton, Nate Zelter, David Hunt +2
Leading autonomous vehicle (AV) platforms and testing infrastructures are, unfortunately, proprietary and closed-source. Thus, it is difficult to evaluate how well safety-critical…
Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment
Qitong Gao, Stephen L. Schimdt, Afsana Chowdhury +6
Deep brain stimulation (DBS) has shown great promise toward treating motor symptoms caused by Parkinson's disease (PD), by delivering electrical pulses to the Basal Ganglia (BG) re…
Stealthy Perception-based Attacks on Unmanned Aerial Vehicles
Amir Khazraei, Haocheng Meng, Miroslav Pajic
In this work, we study vulnerability of unmanned aerial vehicles (UAVs) to stealthy attacks on perception-based control. To guide our analysis, we consider two specific missions: (…
What Would Trojans Do? Exploiting Partial-Information Vulnerabilities in Autonomous Vehicle Sensing
R. Spencer Hallyburton, Qingzhao Zhang, Z. Morley Mao +2
Safety-critical sensors in autonomous vehicles (AVs) form an essential part of the vehicle's trusted computing base (TCB), yet they are highly susceptible to attacks. Alarmingly, T…
Variational Latent Branching Model for Off-Policy Evaluation
Qitong Gao, Ge Gao, Min Chi +1
Model-based methods have recently shown great potential for off-policy evaluation (OPE); offline trajectories induced by behavioral policies are fitted to transitions of Markov dec…
AVstack: An Open-Source, Reconfigurable Platform for Autonomous Vehicle Development
R. Spencer Hallyburton, Shucheng Zhang, Miroslav Pajic
Pioneers of autonomous vehicles (AVs) promised to revolutionize the driving experience and driving safety. However, milestones in AVs have materialized slower than forecast. Two cu…
Attacks on Perception-Based Control Systems: Modeling and Fundamental Limits
Amir Khazraei, Henry Pfister, Miroslav Pajic
We study the performance of perception-based control systems in the presence of attacks, and provide methods for modeling and analysis of their resiliency to stealthy attacks on bo…
Transportation-Inequalities, Lyapunov Stability and Sampling for Dynamical Systems on Continuous State Space
Muhammad Abdullah Naeem, Miroslav Pajic
We study the concentration phenomenon for discrete-time random dynamical systems with an unbounded state space. We develop a heuristic approach towards obtaining exponential concen…
Resiliency of Nonlinear Control Systems to Stealthy Sensor Attacks
Amir Khazraei, Miroslav Pajic
In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy sensor attacks. We start by defining the notion of stealthy attacks in the most…
Optimal Myopic Attacks on Nonlinear Estimation
R. Spencer Hallyburton, Amir Khazraei, Miroslav Pajic
Recent high-profile incidents have exposed security risks in control systems. Particularly important and safety-critical modules for security analysis are estimation and control (E…
Gradient Importance Learning for Incomplete Observations
Qitong Gao, Dong Wang, Joshua D. Amason +6
Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assump…
Security Analysis of Camera-LiDAR Fusion Against Black-Box Attacks on Autonomous Vehicles
R. Spencer Hallyburton, Yupei Liu, Yulong Cao +2
To enable safe and reliable decision-making, autonomous vehicles (AVs) feed sensor data to perception algorithms to understand the environment. Sensor fusion with multi-frame track…
Reinforcement Learning with Temporal Logic Constraints for Partially-Observable Markov Decision Processes
Yu Wang, Alper Kamil Bozkurt, Miroslav Pajic
This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent s…
Formal Verification of Stochastic Systems with ReLU Neural Network Controllers
Shiqi Sun, Yan Zhang, Xusheng Luo +3
In this work, we address the problem of formal safety verification for stochastic cyber-physical systems (CPS) equipped with ReLU neural network (NN) controllers. Our goal is to fi…
Model-Free Learning of Safe yet Effective Controllers
Alper Kamil Bozkurt, Yu Wang, Miroslav Pajic
We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task…
Learning-Based Vulnerability Analysis of Cyber-Physical Systems
Amir Khazraei, Spencer Hallyburton, Qitong Gao +2
This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS). Specifically, we consider a control architecture widely used in CPS (e.g.,…
Learning Optimal Strategies for Temporal Tasks in Stochastic Games
Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos +1
Synthesis from linear temporal logic (LTL) specifications provides assured controllers for systems operating in stochastic and potentially adversarial environments. Automatic synth…
Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learning
Alper Kamil Bozkurt, Yu Wang, Miroslav Pajic
We consider the problem of security-aware planning in an unknown stochastic environment, in the presence of attacks on control signals (i.e., actuators) of the robot. We model the…
Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectives
Alper Kamil Bozkurt, Yu Wang, Michael Zavlanos +1
We study the problem of synthesizing control strategies for Linear Temporal Logic (LTL) objectives in unknown environments. We model this problem as a turn-based zero-sum stochasti…
Probabilistic Conformance for Cyber-Physical Systems
Yu Wang, Mojtaba Zarei, Borzoo Bonakdarpoor +1
In system analysis, conformance indicates that two systems simultaneously satisfy the same set of specifications of interest; thus, the results from analyzing one system automatica…
Context-Aware Temporal Logic for Probabilistic Systems
Mahmoud Elfar, Yu Wang, Miroslav Pajic
In this paper, we introduce the context-aware probabilistic temporal logic (CAPTL) that provides an intuitive way to formalize system requirements by a set of PCTL objectives with…