Running
🧠
LLMEvaluationReports
Threat Modelling (Malicious Actors & Online Harms)
Broderick McDonald
BroderickMcDonald
AI & ML interests
Oxford / Kings College London — Algorithmic Content Detection, Hash-Sharing, Evasion Tactics, Adversarial Red Teaming, Online Extremism, Disinformation, Bias
Organizations
