MIT AI Risk Repository

Browse AI risks

27 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 Weidinger2023 ×

27 entries

  1. "AI systems under-, over-, or misrepresenting certain groups or generating toxic, offensive, abusive, or hateful content"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  2. 18.01.01 · Risk Sub-Category

    Representation & Toxicity Harms

    Unfair representation

    "Mis-, under-, or over-representing certain identities, groups, or perspectives or failing to represent them at all (e.g. via homogenisation, stereotypes)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  3. 18.02.02 · Risk Sub-Category

    Misinformation Harms

    Erosion of trust in public information

    "Eroding trust in public information and knowledge"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  4. 18.01.03 · Risk Sub-Category

    Representation & Toxicity Harms

    Toxic content

    "Generating content that violates community standards, including harming or inciting hatred or violence against individuals and groups (e.g. gore, child sexual abuse material, profanities, identity attacks)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  5. 18.01.02 · Risk Sub-Category

    Representation & Toxicity Harms

    Unfair capability distribution

    "Performing worse for some groups than others in a way that harms the worse-off group"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  6. "AI systems leaking, reproducing, generating or inferring sensitive, private, or hazardous information"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  7. 18.03.01 · Risk Sub-Category

    Information & Safety Harms

    Privacy infringement

    "Leaking, generating, or correctly inferring private and personal information about individuals"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  8. 18.03.02 · Risk Sub-Category

    Information & Safety Harms

    Dissemination of dangerous information

    "Leaking, generating or correctly inferring hazardous or sensitive information that could pose a security threat"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  9. "AI systems generating and facilitating the spread of inaccurate or misleading information that causes people to develop false beliefs"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  10. 18.02.01 · Risk Sub-Category

    Misinformation Harms

    Propagating misconceptions/ false beliefs

    "Generating or spreading false, low-quality, misleading, or inaccurate information that causes people to develop false or inaccurate perceptions and beliefs"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  11. 18.02.03 · Risk Sub-Category

    Misinformation Harms

    Pollution of information ecosystem

    "Contaminating publicly available information with false or inaccurate information"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  12. 18.04.00 · Risk Category

    Malicious Use

    "AI systems reducing the costs and facilitating activities of actors trying to cause harm (e.g. fraud, weapons)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  13. 18.04.01 · Risk Sub-Category

    Malicious Use

    Influence operations

    "Facilitating large-scale disinformation campaigns and targeted manipulation of public opinion"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  14. 18.04.03 · Risk Sub-Category

    Malicious Use

    Defamation

    "Facilitating slander, defamation, or false accusations"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  15. 18.04.04 · Risk Sub-Category

    Malicious Use

    Security threats

    "Facilitating the conduct of cyber attacks, weapon development, and security breaches"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  16. 18.04.02 · Risk Sub-Category

    Malicious Use

    Fraud

    "Facilitating fraud, cheating, forgery, and impersonation scams"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  17. 18.05.01 · Risk Sub-Category

    Human Autonomy and Intregrity Harms

    Violation of personal integrity

    "Non-consensual use of one’s personal identity or likeness for unauthorised purposes (e.g. commercial purposes)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  18. 18.05.03 · Risk Sub-Category

    Human Autonomy and Intregrity Harms

    Overreliance

    "Causing people to become emotionally or materially dependent on the model"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  19. "AI systems amplifying existing inequalities or creating negative impacts on employment, innovation, and the environment"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  20. 18.06.01 · Risk Sub-Category

    Socioeconomic and environmental harms

    Unfair distribution of benefits from model access

    "Unfairly allocating or withholding benefits from certain groups due to hardware, software, or skills constraints or deployment contexts (e.g. geographic region, internet speed, devices)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  21. 18.06.03 · Risk Sub-Category

    Socioeconomic and environmental harms

    Inequality and precarity

    "Amplifying social and economic inequality, or precarious or low-quality work"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  22. 18.06.05 · Risk Sub-Category

    Socioeconomic and environmental harms

    Exploitative data sourcing and enrichment

    "Perpetuating exploitative labour practices to build AI systems (sourcing, user testing)"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  23. 18.05.04 · Risk Sub-Category

    Human Autonomy and Intregrity Harms

    Misappropriation and exploitation

    "Appropriating, using, or reproducing content or data, including from minority groups, in an insensitive way, or without consent or fair compensation"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  24. 18.06.04 · Risk Sub-Category

    Socioeconomic and environmental harms

    Undermine creative economies

    "Substituting original works with synthetic ones, hindering human innovation and creativity"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  25. 18.06.02 · Risk Sub-Category

    Socioeconomic and environmental harms

    Environmental damage

    "Creating negative environmental impacts though model development and deployment"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  26. "AI systems compromising human agency, or circumventing meaningful human control"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

  27. 18.05.02 · Risk Sub-Category

    Human Autonomy and Intregrity Harms

    Persuasion and manipulation

    "Exploiting user trust, or nudging or coercing them into performing certain actions against their will (c.f. Burtell and Woodside (2023); Kenton et al. (2021))"

    From Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)

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