MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
- 2024
- AIES 2024
Mark manages the AI Security & Privacy team in the Dublin Research Lab. The research topics for the team are AI Security (which focuses on the robustness of AI models), Privacy Enhancing Technologies (de-identification, risk assessment, Differential Privacy). Over a career spanning 30 years, Mark has researched solutions for several industries, including: Financial Services (HPC), Marine Environmental (IoT) and Smarter Cities. In more recent years, Mark's research focused on the intersection of Analytics/AI with modern cloud technologies.