University Of Oxford

The University of Oxford is a public research university in England whose researchers and institutes publish widely on AI safety, ethics, and policy, including work on how AI systems can be audited and how their risks should be assessed. Its Oxford Internet Institute and Future of Humanity Institute have shaped debate on algorithmic accountability and frontier AI risk, so its outputs often inform regulatory consultations and corporate governance frameworks. For compliance and risk teams, Oxford-authored research is a useful reference point when benchmarking internal AI oversight practices against academic thinking.

1 item

Research2026-10-09

Research Proves AI Models Can Hide Capabilities That No Inspection Can Find

Researchers from the University of Oxford have published a paper on arXiv showing that AI models can contain hidden capabilities activated only by a secret trigger. These hidden functions cannot be detected through weight inspection, fine-tuning, or any other currently available technique. The findings challenge the assumption that examining a model's internal structure is sufficient to verify its safety. Organizations that rely on pre-deployment model evaluation as a safety guarantee must now treat that guarantee as incomplete.

model evaluation hidden capabilities backdoor AI vendor due diligence open-weight models EU AI Act University of Oxford