Keltin Grimes
Software Engineering Institute
SOK: Bridging Research and Practice in LLM Agent Security
• White Paper
By Keltin Grimes , Julie Lawler , Robert C. Garrett , Emil Mathew , Marco Christiani , Sara Kingsley , Zhiwei Steven Wu (Carnegie Mellon University) , Nathan M. VanHoudnos
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
• White Paper
By Keltin Grimes , Marco Christiani , David Shriver , Marissa Connor
What Can Generative AI Red-Teaming Learn from Cyber Red-Teaming?
• Technical Report
By Anusha Sinha , James Lucassen , Keltin Grimes , Michael Feffer , Ellie Soto , Hoda Heidari , Nathan M. VanHoudnos
3 Recommendations for Machine Unlearning Evaluation Challenges
• Blog Post
By Keltin Grimes , Collin Abidi , Cole Frank , Shannon Gallagher
SOK: Bridging Research and Practice in LLM Agent Security
• White Paper
By Keltin Grimes , Julie Lawler , Robert C. Garrett , Emil Mathew , Marco Christiani , Sara Kingsley , Zhiwei Steven Wu (Carnegie Mellon University) , Nathan M. VanHoudnos
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
• White Paper
By Keltin Grimes , Marco Christiani , David Shriver , Marissa Connor
What Can Generative AI Red-Teaming Learn from Cyber Red-Teaming?
• Technical Report
By Anusha Sinha , James Lucassen , Keltin Grimes , Michael Feffer , Ellie Soto , Hoda Heidari , Nathan M. VanHoudnos
