7 papers
Privacy-Preserving Robustness-Guided Testing
Charles Koll, Houssam Abbas, Mike Rosulek
In industries like semi-conductors and aerospace, it is common for the design company to contract out part of the testing process to a Testing-as-a-Service (TaaS) company. In such…
Runtime Monitoring of Distributed Cyber-Physical Systems Without a Global Clock
Charles Koll, Houssam Abbas
We give the first theoretical characterization, and the first algorithm, for continuous monitoring of a distributed Cyber-Physical System (CPS) against a dense-time temporal logic…
Deontically Constrained Policy Improvement in Reinforcement Learning Agents
Alena Makarova, Houssam Abbas
Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures non-determinism, probabilistic u…
Monitoring in the Dark: Privacy-Preserving Runtime Verification of Cyber-Physical Systems
Charles Koll, Preston Tan Hang, Mike Rosulek +1
In distributed Cyber-Physical Systems and Internet-of-Things applications, the nodes of the system send measurements to a monitor that checks whether these measurements satisfy giv…
ROS2-Based Simulation Framework for Cyberphysical Security Analysis of UAVs
Unmesh Patil, Akshith Gunasekaran, Rakesh Bobba +1
We present a new simulator of Uncrewed Aerial Vehicles (UAVs) that is tailored to the needs of testing cyber-physical security attacks and defenses. Recent investigations into UAV…
Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates
Colin Shea-Blymyer, Houssam Abbas
When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually…
Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
Amelia Kawasaki, Andrew Davis, Houssam Abbas
The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these mode…