Data Privacy

Bayesian Decision-Theoretic Privacy

Christian P. Robert, Full Professor, Department of Applied Mathematics (CEREMADE), Paris Dauphine-PSL University;

Nov 2, 12:00 - 13:00

B3 R5209

Data Privacy statistical privacy bayesian adversial privacy privacy-preserving machine learning privacy-preserving AI bayesian methods

This seminar introduces two Bayesian decision-theoretic frameworks, persuasive privacy and Bayesian adversarial privacy, that quantify statistical privacy by evaluating how data releases influence adversarial beliefs and decisions while offering contextual alternatives to conventional differential privacy.

Private and Robust Learning for Decision Making

Yulian Wu, Ph.D. Student, Computer Science

Apr 14, 15:00 - 17:00

B4 R5220; Zoom Meeting 98132861421

decision making Trustworthy AI privacy-preserving AI Data Privacy machine learning artificial intelligence AI

This thesis develops the theoretical foundations of decision-making under privacy, heavy-tailed feedback, and data contamination, establishing fundamental limits and designing near-optimal algorithms across bandits, reinforcement learning, and RLHF.

Provable and Measurable Machine Unlearning in Modern Learning Systems

Cheng-Long Wang, Ph.D. Student, Computer Science

Mar 10, 10:30 - 12:30

B2 L5 R5209

Machine Unlearning Data Privacy Trustworthy AI Federated learning machine learning AI

This dissertation examines the foundations of machine unlearning under realistic learning system constraints and proposes both theoretically grounded unlearning algorithms and principled evaluation frameworks for modern learning systems.

CybeResil Research Opportunities

intrusion tolerance fault tolerance trusted execution environments Data Privacy intrusion detection software verification

Broad Research Topics Robust and Adaptive Fault and Intrusion Tolerance; Ultra-Reliable Micro Trusted Execution Environments; Privacy and Integrity-preserving Data Processing; Next-generation Threat and Intrusion Detection / Prevention Systems; High-confidence Vertical Software Verification. Focused PhD-level Research Opportunities Fault and Intrusion Resilience Systems for Modern Vehicles Modern software-defined vehicles are prone to software faults and intrusions. A modern vehicle is composed of up to hundred commuting units, called Electronic Control Units (ECUs), connected via different

Cheng-Long Wang

Ph.D. Student, Computer Science

Machine Unlearning Data Privacy Trustworthy AI Federated learning

Cheng-Long Wang is a PhD candidate in Computer Science at King Abdullah University of Science and Technology (KAUST), advised by Prof. Di Wang.