Connor, Marissa Catherine

3 publications

ICLR 2025 Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing Keltin Grimes, Marco Christiani, David Shriver, Marissa Catherine Connor

ICLRW 2023 Exploring Vulnerabilities of Semi-Supervised Learning to Simple Backdoor Attacks Marissa Catherine Connor, Vincent Emanuele

TMLR 2023 Learning Identity-Preserving Transformations on Data Manifolds Marissa Catherine Connor, Kion Fallah, Christopher John Rozell