3 papers
cs.AI2026
Securing Dual-Use Pathogen Data of Concern
Doni Bloomfield, Allison Berke, Moritz S. Hanke +6
Training data is an essential input into creating competent artificial intelligence (AI) models. AI models for biology are trained on large volumes of data, including data related…
cs.LG2025
Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning
James R. M. Black, Moritz S. Hanke, Aaron Maiwald +3
Novel deep learning architectures are increasingly being applied to biological data, including genetic sequences. These models, referred to as genomic language models (gLMs), have…
cs.CY2024
Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models
Jaspreet Pannu, Doni Bloomfield, Alex Zhu +4
As a result of rapidly accelerating AI capabilities, over the past year, national governments and multinational bodies have announced efforts to address safety, security and ethics…