Attack, Defense, and Mechanistic Taxonomy of Protein Language Model Biosecurity

safely.bio: Customer screening for DNA synthesis providers

Deploying customer screening software at DNA synthesis providers to reduce AI-enabled biothreats

Safeguarding DNA Synthesis from Biological Risks Posed by Advanced AI

We will test whether circuits in protein language models can detect function-preserving redesigns of known toxins that evade homology-based DNA-synthesis screen

BioRAG-Guard: Poisoning Evals for Biological AI Agents

An open-source benchmark and defense toolkit for testing whether corrupted biological databases can hijack retrieval-augmented AI agents used in genomics, prote

Contamination-Safe Continual Learning for AI Guard Models

Turning evolving attacks into clean training data without memorization, evaluation leakage, overblocking, or forgetting.

Continued funding for a PhD in AI x-risk decision and risk analysis

Continuation of a previous grant to allow me to pursue a PhD in risk and decision analysis related to AI x-risks

Emergent misalignment and memetic replication in multi-agent codebases