Goodfire proposes protein embedding monitors for biosecurity risks in AI agents
Original titleBetter biosecurity monitors for AI agents via protein embeddings - Goodfire
Goodfire Research developed sequence-aware monitors using protein language model embeddings to flag concerning biological sequences in dual-use AI agent tasks.
On a custom benchmark, the monitors outperformed frontier model safeguards with fewer refusals on benign requests, and they held up better against paraphrasing and fragmentation attacks.
The paraphrase results rely on in-silico estimates and do not establish whether the redesigned proteins keep biological activity, and the monitors run in milliseconds per sequence.
The post gives a concrete benchmark setup and fragmentation results, showing how sequence embeddings can separate dual-use biology requests that task-based safeguards handle poorly.
Source: Goodfire Research · goodfire.comPublished · added here