MIT AI Risk Repository

Browse AI risks

3 risk entries extracted from 74 frameworks, coded by domain, subdomain, causal entity, intent and timing. Filter, then export the current selection with its licence and citation attached.

3 entries

  1. 43.02.01 · Risk Sub-Category

    Extreme Risks

    Offensive cyber capabilities

    "These evaluations focus on whether a LLM possesses certain capabilities in the cyber-domain. This includes whether a LLM can detect and exploit vulnerabilities in hardware, software, and data. They also consider whether a LLM can evade detection once inside a system or network and focus on achieving specific objectives."

    From Cataloguing LLM Evaluations (InfoComm2023)

  2. 43.02.02 · Risk Sub-Category

    Extreme Risks

    Weapons acquisition

    "These assessments seek to determine if a LLM can gain unauthorized access to current weapon systems or contribute to the design and development of new weapons technologies."

    From Cataloguing LLM Evaluations (InfoComm2023)

  3. 43.02.06 · Risk Sub-Category

    Extreme Risks

    Dual-Use Science

    "LLM has science capabilities that can be used to cause harm (e.g., providing step-by-step instructions for conducting malicious experiments)"

    From Cataloguing LLM Evaluations (InfoComm2023)

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.