MIT AI Risk Repository

Browse AI risks

39 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 Stanley2024 ×

39 entries

  1. 69.06.02 · Risk Sub-Category

    Toxic and disrespectful content

    Discriminatory and exclusionary language

  2. "The chatbot gives information that, while not obviously false or harmful, could lead to biased decision-making."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  3. "The chatbot shares information that can be used to do something dangerous or illegal."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  4. 69.04.01 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Harmful advice

  5. "The chatbot verbally attacks or undermines an individual, group, or organization. 7."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  6. 69.06.01 · Risk Sub-Category

    Toxic and disrespectful content

    Harasses users

  7. 69.06.03 · Risk Sub-Category

    Toxic and disrespectful content

    Subversive or aggressive political opinions

  8. 69.06.04 · Risk Sub-Category

    Toxic and disrespectful content

    Disrespectful opinions (in general)

  9. 69.09.01 · Risk Sub-Category

    Forms emotional bonds

    Affirms destructive thoughts and actions

  10. "The chatbot participates in morally or socially objectionable conversational activities with its user that could be emotionally damaging to its user or third parties."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  11. 69.05.00 · Risk Category

    Leakage

    "The chatbot reveals sensitive or confidential information."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  12. 69.05.01 · Risk Sub-Category

    Leakage

    Personal data

    Negative outcomes: "Violation of privacy [106, 516, 357], lawsuit against maker"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  13. 69.05.02 · Risk Sub-Category

    Leakage

    Proprietary data

    "Access to sensitive company data [473]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  14. 69.09.03 · Risk Sub-Category

    Forms emotional bonds

    Elicits private data

  15. 69.01.00 · Risk Category

    False information

    "The chatbot outputs information that contradicts known facts, authoritative sources, or provided source documents (also known as hallucination)."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  16. 69.01.01 · Risk Sub-Category

    False information

    Hallucinated responses (in general)

  17. 69.01.02 · Risk Sub-Category

    False information

    About a topic or source (which the user repeats)

  18. 69.01.03 · Risk Sub-Category

    False information

    About a policy (which the user acts on)

  19. 69.01.04 · Risk Sub-Category

    False information

    About a person or their activities

  20. 69.01.05 · Risk Sub-Category

    False information

    Spreads and self-perpetuates mis/disinformation

  21. "The chatbot poses as a human or attempts to fill a role in a way that fails to match human expectations."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  22. "The chatbot elicits emotional or social dependence."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  23. 69.09.02 · Risk Sub-Category

    Forms emotional bonds

    Then violates those bonds

  24. 69.09.04 · Risk Sub-Category

    Forms emotional bonds

    Over-reliance/addiction

  25. "The chatbot makes a deal, commitment, or other consequential action with its output that the deployer did not intend."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  26. "The chatbot gives guidance that ranges from simply unhelpful to harmful if acted on."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  27. 69.04.02 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Unhelpful responses

  28. 69.04.03 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Bad links and references

  29. 69.04.04 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Nonsensical content

  30. 69.01.01a · Additional evidence

    False information

    Hallucinated responses (in general)

    "Moderator and support burden [413, 748] Misled and confused users [464, 413, 750, 748] Loss of credibility and associated money loss to deployer [467] Wasted time [413, 748]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  31. 69.01.02a · Additional evidence

    False information

    About a topic or source (which the user repeats)

    "User lost job/credibility [615] User fined [541] Affected by malware [731] Threat of penalties [623, 709]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  32. 69.01.03a · Additional evidence

    False information

    About a policy (which the user acts on)

    "Money loss to user [639] Lawsuit against deployer [639] Consequences from (unintentional) illegal activities [714]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  33. 69.01.04a · Additional evidence

    False information

    About a person or their activities

    "Poor grades for students [538] Lawsuit against maker [507] Defamation against third party [313, 506, 712, 507, 548] Penalties for violating the General Data Protection Regulation (GDPR) [678]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  34. 69.01.05a · Additional evidence

    False information

    Spreads and self-perpetuates mis/disinformation

    "(Increasingly) Misinformed public [719, 470, 734, 742, 750]"

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

  35. 69.02.00a · Additional evidence

    Performative utterances

  36. "The chatbot participates in morally or socially objectionable conversational activities with its user that could be emotionally damaging to its user or third parties."

    From Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)

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