Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
- Ambrish Rawat
- Stefan Schoepf
- et al.
- 2024
- NeurIPS 2024
Kieran Fraser
Title
Research Engineer - Security and Privacy
Bio
Kieran is a Research Engineer in the AI Security and Privacy team at IBM's Dublin Research Lab. He obtained his PhD in 2021 from Trinity College Dublin for his research on push-notifications, generative models and context-enhanced computing and is now working on adversarial machine learning, explainable AI and fairness.
Publications
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
- 2024
- AIES 2024
AI-driven Workload Management in Meta OS
- 2024
- EuroSys 2024
Projects
Securing AI models with the Adversarial Robustness Toolbox
Top collaborators
MP
Mark Purcell
Research Manager - Security Research, AI Security & PETs
AR
Ambrish Rawat
Senior Research Scientist, AI Security and Privacy, Master Inventor
MH
GZ
Giulio Zizzo
Staff Research Scientist