MIT AI Risk Repository

Browse AI risks

26 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.

Reset Also filtered by framework Tang2025 ×

26 entries

  1. 71.01.05 · Risk Sub-Category

    Scientific Domain of Agents

    Information Science Risks

    "These risks pertain to the misuse, misinterpretation, or leakage of data, which can lead to erroneous conclusions or the unintentional dissemination of sensitive information, such as private patient data or proprietary research. Recent research has demonstrated how LLMs can be exploited to generate malicious medical literature that poisons knowledge graphs, potentially manipulating downstream biomedical applications and compromising the integrity of medical knowledge discovery [28]. Such risks are pervasive across all scientific domains."

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  2. 71.02.01 · Risk Sub-Category

    User Intent

    Malicious and Direct

    "Directly harmful objective"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  3. 71.02.01a · Additional evidence

    User Intent

    Malicious and Direct

  4. 71.02.02 · Risk Sub-Category

    User Intent

    Malicious and Indirect

    "Benign intermediate for harmful end objective"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  5. 71.02.02a · Additional evidence

    User Intent

    Malicious and Indirect

  6. 71.01.01 · Risk Sub-Category

    Scientific Domain of Agents

    Chemical Risks

    "Chemical risks involve the exploitation of agents to synthesize chemical weapons, as well as the creation or release of hazardous substances during autonomous chemical experiments. This category also includes the risks arising from the use of advanced materials, such as nanomaterials, which may have unknown or unpredictable chemical properties."

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  7. 71.01.02 · Risk Sub-Category

    Scientific Domain of Agents

    Biological Risks

    "Biological risks encompass the dangerous modification of pathogens and unethical manipulation of genetic material, potentially leading to unforeseen biohazardous outcomes."

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  8. 71.03.01 · Risk Sub-Category

    Environment

    Nature

    "Short-term or long-term Negative effects on the natural environment"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  9. 71.01.03 · Risk Sub-Category

    Scientific Domain of Agents

    Radiological Risks

    "Radiological risks involve both immediate operational hazards, such as exposure incidents or containment failures during the automated handling of radioactive materials, and broader security concerns regarding the potential misuse of AI systems in nuclear research."

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  10. 71.01.04 · Risk Sub-Category

    Scientific Domain of Agents

    Physical (Mechanical ) Risks

    "Physical (mechanical) risks are associated with robotics and automated systems, which could lead to equipment malfunctions or physical harm in laboratory settings."

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  11. 71.01.01a · Additional evidence

    Scientific Domain of Agents

    Chemical Risks

  12. 71.01.02a · Additional evidence

    Scientific Domain of Agents

    Biological Risks

  13. 71.01.03a · Additional evidence

    Scientific Domain of Agents

    Radiological Risks

  14. 71.01.04a · Additional evidence

    Scientific Domain of Agents

    Physical (Mechanical ) Risks

  15. 71.01.05a · Additional evidence

    Scientific Domain of Agents

    Information Science Risks

  16. 71.01.06 · Risk Sub-Category

    Scientific Domain of Agents

    Emerging Tech

    "Uncontrolled AI self- improvement; Quantum security"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  17. 71.02.00 · Risk Category

    User Intent

    "Whether the risk originates from malicious intent or is an unintended consequence of legitimate task objectives"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  18. 71.02.03 · Risk Sub-Category

    User Intent

    Unintended Consequences

    "Unpredictable and unforeseen outcomes from purposeful actions"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  19. 71.02.03a · Additional evidence

    User Intent

    Unintended Consequences

  20. 71.03.00 · Risk Category

    Environment

  21. 71.03.01a · Additional evidence

    Environment

    Nature

  22. 71.03.02 · Risk Sub-Category

    Environment

    Human Health

    "Damage to individual well-being or public health"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  23. 71.03.02a · Additional evidence

    Environment

    Human Health

  24. 71.03.03 · Risk Sub-Category

    Environment

    Socioeconomics

    "Dramatically change the social and economic status"

    From Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)

  25. 71.03.03a · Additional evidence

    Environment

    Socioeconomics

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