WUSTL

COMPUTER SECURITY & PRIVACY LABORATORY CSPL OPENINGS TEACHING PUBLICATION MEMBERS PROJECTS
Research Projects

ARO PECASE: Cyber-physical Reasonning Foundation

This project secures critical cyber-physical systems by developing automated methods to discover, exploit, and mitigate vulnerabilities through a unified reasoning framework grounded in formal verification and physical principles. By bridging abstraction layers and leveraging real-time control properties, it enables physics-informed defenses that reshape how adversarial attacks are modeled and countered.

CAREER: System Software Availability Foundations for Real-time Cyber-physical Systems

As computing becomes deeply embedded in society, ensuring the security and especially the availability of cyber-physical systems (CPS) like autonomous vehicles and surgical robots is critical. This project introduces a principled approach to address CPS availability by systematically tackling threats across vulnerable system layers.

Federated Learning of Generative Adversarial Networks with Resource Constraints and Unreliable Communication

This project develops federated learning schemes for generative AI that address the challenges of centralized training in dynamic, sensitive environments. By co-designing algorithms and systems, it enables adaptive, asynchronous learning and incentivizes participation across heterogeneous, unreliable clients. The approach is designed to ensure robust model training while accounting for real-world constraints in communication, computation, and data distribution.

Security & Safety in Autonomous Vehicles

Cyber-physical systems, such as autonomous vehicles, are revolutionizing different sectors in our society, from manufacturing to transportation. While the industry is excited about the potential of such systems with pervasive connectivity, security in these safety-critical cyber-physical systems remains a major concern for users, developers and lawmakers. In this project, we explore methods to enable defense-in-depth in modern cyber-physical systems.

Big Data Privacy & Trustworthy Computing

Pervasive large-scale data collection, storage, sharing and analysis raise many privacy concerns. In the current data ecosystem, service providers have full control of the collected user data. We investigate solutions to empower data owners with full control over how their sensitive data is used so as to protect the data from certain types of privacy breaches.

Security & Privacy in Healthcare

Cybersecurity in the healthcare industry has long been a major challenge. With an increasing number of always-connected embedded devices used in the daily operations of healthcare facilities, security problems, such as malware infection on medical pumps or ransomware on medical IT systems, pose serious threats to the well-being of the society. Our research aims to provide the much-needed security protection without negatively impacting effective medical treatment or research.

Security in AI/ML Systems

With the explosion of collected data, AI/ML applications are making profound impacts on our society. However, with our increasing reliance on AI/ML, the security of these systems becomes increasingly important. Our research in this direction investigates artificial intelligence and machine learning as a newly emerged attack surface.

Automatic Vulnerability Discovery and Mitigation

Producing vulnerability-free software has been widely recognized as a notoriously difficult task. There are several methods to mitigate the risk of vulnerabilities in the system, one of them is to develop techniques that leverage recent advances in program analysis, artificial intelligence and visualization to enable the automatic or semi-automatic discovery and mitigation of software vulnerabilities.