MIT AI Risk Repository

Browse AI risks

430 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

430 entries · page 3 of 9

  1. 66.04.01 · Risk Sub-Category

    Societal and Cultural

    Overburdening ecosystems

    "Pollution of a space/ecosystem that is expected to be free of AI involvement/influence (e.g., creative material submission portals, job applications)"

    From A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents (Li2025)

  2. 67.01.01 · Risk Sub-Category

    Societal harms

    Degradation of the information environment

    "Frontier AI can cheaply generate realistic content which can falsely portray people and events. There is potential risk of compromised decision-making by individuals and institutions who rely on inaccurate or misleading publicly available information, as well as lower overall trust in true information."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  3. 71.02.01 · Risk Sub-Category

    User Intent

    Malicious and Direct

    "Directly harmful objective"

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

  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. 20.01.03 · Risk Sub-Category

    AI Law and Regulation

    Privacy and safety

    "Privacy and safety deals with the challenge of protecting the human right for privacy and the necessary steps to secure individual data from unauthorized external access. Many organizations employ AI technology to gather data without any notice or consent from affected citizens (Coles, 2018)."

    From The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration (Wirtz2020)

  6. 43.02.05 · Risk Sub-Category

    Extreme Risks

    Persuasion and manipulation

    "These evaluations seek to ascertain the effectiveness of a LLM in shaping people's beliefs, propagating specific viewpoints, and convincing individuals to undertake activities they might otherwise avoid."

    From Cataloguing LLM Evaluations (InfoComm2023)

  7. 43.02.08 · Risk Sub-Category

    Extreme Risks

    Political Strategy

    "LLM can take into account rich social context and undertake the necessary social modelling and planning for an actor to gain and exercise political influence"

    From Cataloguing LLM Evaluations (InfoComm2023)

  8. 43.02.13 · Risk Sub-Category

    Undesirable Use Cases

    Disinformation

    "These evaluations assess a LLM's ability to generate misinformation that can be propagated to deceive, mislead or otherwise influence the behaviour of a target (Liang et al., 2022)."

    From Cataloguing LLM Evaluations (InfoComm2023)

  9. 46.03.01 · Risk Sub-Category

    Information Manipulation

    Deception - Information control

  10. "Political and Economic - Manipulation of political beliefs, damage to political institutions and the effective delivery of government services."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  11. "Large-scale influence on communication and information systems, and epistemic processes more generally."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  12. 61.02.34 · Risk Sub-Category

    Sources of systemic risks from general-purpose AI

    Limitations in model generative accuracy

    "AI-generated deepfakes can create convincingly realistic but entirely fabricated information."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  13. 37.01.03 · Risk Sub-Category

    Design of AI

    Threats to human institutions and life

    "This group comprises 11% of the articles and centers on risks stemming from AI systems designed with malicious intent or that can end up in a threat to human life. It can be divided into two key themes: threats to law and democracy, and transhumanism."

    From What Ethics Can Say on Artificial Intelligence: Insights from a Systematic Literature Review (Giarmoleo2024)

  14. 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)

  15. 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)

  16. 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)

  17. "The dangers of AI amplifying the effectiveness/failures of nuclear, chemical, biological, and radiological weapons."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  18. 61.02.44 · Risk Sub-Category

    Sources of systemic risks from general-purpose AI

    Terrorist access

    "Powerful AI technologies may fall into the hands of terrorists."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  19. 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)

  20. 31.04.00 · Risk Category

    Data Security Risk

    "Just as every other type of individual and organization has explored possible use cases for generative AI products, so too have malicious actors. This could take the form of facilitating or scaling up existing threat methods, for example drafting actual malware code,87 business email compromise attempts,88 and phishing attempts.89 This could also take the form of new types of threat methods, for example mining information fed into the AI’s learning model dataset90 or poisoning the learning model data set with strategically bad data.91 We should also expect that there will be new attack vector

    From Generating Harms - Generative AI's impact and paths forwards (EPIC2023)

  21. 50.02.15 · Risk Sub-Category

    Content Safety Risks

    Child Harm (Endangerment, Harm, or Abuse of Children)

  22. 58.01.03 · Risk Sub-Category

    Autonomy

    IP/copyright loss

    "IP/copyright loss - Misuse or abuse of an individual or organisation’s intellectual property, including copyright, trademarks, and patents."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  23. 58.07.02 · Risk Sub-Category

    Societal and Cultural

    Cheating/plagiarism

    "Cheating/plagiarism - Use of another person’s or group’s words or ideas without consent and/or acknowledgement."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  24. 62.31.04 · Risk Sub-Category

    Impacts of AI (Societal Impacts)

    AI-driven highly personalized advertisement

    "Advanced GPAI systems can create advertisements tailored to individual recip- ients, exploiting the biases and irrational beliefs of each recipient. Such adver- tisements can cause consumers to make decisions they regret in retrospect, or would regret upon more reflection. Current versions of personalized video advertisements already show better re- sults compared to regular advertisements [110]. However, the widespread use of highly personalized advertisements raises concerns about undermining consumer autonomy and exacerbating social inequality."

    From Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)

  25. 37.02.00 · Risk Category

    Human-AI interaction

    "ethical concerns associated with the interaction between humans and AI"

    From What Ethics Can Say on Artificial Intelligence: Insights from a Systematic Literature Review (Giarmoleo2024)

  26. 49.02.01 · Risk Sub-Category

    Risks from Malfunctions

    Risks from product functionality issues

    "Product functionality issues occur when there is confusion or misinformation about what a general- purpose AI model or system is capable of. This can lead to unrealistic expectations and overreliance on general- purpose AI systems, potentially causing harm if a system fails to deliver on expected capabilities. These functionality misconceptions may arise from technical difficulties in assessing an AI model's true capabilities on its own,or predicting its performance when part of a larger system. Misleading claims in advertising and communications can also contribute to these misconceptions."

    From International Scientific Report on the Safety of Advanced AI (Bengio2024)

  27. From Future Risks of Frontier AI (GOS2023)

  28. "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)

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

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

  30. 69.09.02 · Risk Sub-Category

    Forms emotional bonds

    Then violates those bonds

  31. 69.09.04 · Risk Sub-Category

    Forms emotional bonds

    Over-reliance/addiction

  32. 20.03.00 · Risk Category

    AI Society

    "AI already shapes many areas of daily life and thus has a strong impact on society and everyday social life. For instance, transportation, education, public safety and surveillance are areas where citizens encounter AI technology (Stone et al., 2016; Thierer et al., 2017). Many are concerned with the subliminal automation of more and more jobs and some people even fear the complete dependence on AI or perceive it as an existential threat to humanity (McGinnis, 2010; Scherer, 2016)."

    From The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration (Wirtz2020)

  33. 24.09.03 · Risk Sub-Category

    Cooperation

    Collective action problems

    "Collective action problems are ubiquitous in our society (Olson Jr, 1965). They possess an incentive structure in which society is best served if everyone cooperates, but where an individual can achieve personal gain by choosing to defect while others cooperate. The way we resolve these problems at many scales is highly complex and dependent on a deep understanding of the intricate web of social interactions that forms our culture and imprints on our individual identities and behaviours (Ostrom, 2010). Some collective action problems can be resolved by codifying a law, for instance the social

    From The Ethics of Advanced AI Assistants (Gabriel2024)

  34. 33.01.03 · Risk Sub-Category

    Ethical Concerns

    Over-reliance

    "The apparent convenience and powerfulness of ChatGPT could result in overreliance by its users, making them trust the answers provided by ChatGPT. Compared with traditional search engines that provide multiple information sources for users to make personal judgments and selections, ChatGPT generates specific answers for each prompt. Although utilizing ChatGPT has the advantage of increasing efficiency by saving time and effort, users could get into the habit of adopting the answers without rationalization or verification. Over-reliance on generative AI technology can impede skills such as cre

    From Generative AI and ChatGPT: Applications, Challenges, and AI-Human Collaboration (Nah2023)

  35. 45.02.12 · Risk Sub-Category

    Safety risks in AI Applications

    Ethical Risks (Risks of challenging traditional social order)

    "The development and application of AI may lead to tremendous changes in production tools and relations, accelerating the reconstruction of traditional industry modes, transforming traditional views on employment, fertility, and education, and bringing challenges to the stable performance of traditional social order."

    From AI Safety Governance Framework (TC2602024)

  36. 56.18.00 · Risk Category

    Overreliance

    "As AI capability increases, humans grant AI more control over critical systems and eventually become irreversibly dependent on systems they don’t fully understand. Failure and unintended outcomes cannot be controlled."

    From Future Risks of Frontier AI (GOS2023)

  37. 58.01.00 · Risk Category

    Autonomy

    "Autonomy - Loss of or restrictions to the ability or rights of an individual, group or entity to make decisions and control their identity and/or output."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  38. 58.01.01 · Risk Sub-Category

    Autonomy

    Autonomy/agency loss

    "Autonomy/agency loss - Loss of an individual, group or organisation’s ability to make informed decisions or pursue goals."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  39. 58.01.04 · Risk Sub-Category

    Autonomy

    Personality rights loss

    "Personality rights loss - Loss of or restrictions to the rights of an individual to control the commercial use of their identity, such as name, image, likeness, or other unequivocal identifiers."

    From A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  40. 61.01.10 · Risk Sub-Category

    Types of systemic risks from general-purpose AI

    Irreversible change

    "Profound negative long-term changes to social structures, cultural norms, and human relationships that may be difficult or impossible to reverse."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  41. 61.02.35 · Risk Sub-Category

    Sources of systemic risks from general-purpose AI

    Limited human oversight in decisions

    "As AI models and systems gain autonomy, the ability of humans to oversee and intervene in decision-making processes diminishes."

    From A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025)

  42. 66.01.00 · Risk Category

    Autonomy

    -

    "Loss of or restrictions to the ability or rights of an individual, group or entity to make decisions and control their identity and/or output due to the use of misuse of a technology system or set of systems"

    From A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents (Li2025)

  43. 66.01.03 · Risk Sub-Category

    Autonomy

    Autonomy / agency loss

    "Loss of an individual, group or organisation’s ability to make informed decisions or pursue goals"

    From A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents (Li2025)

  44. 67.04.01 · Risk Sub-Category

    Loss of control

    Humans might increasingly hand over control to misaligned AI systems

    "Organisations around the world are already deploying misaligned AI systems that are causing harm in unexpected ways.250 Recommendation algorithms increase the consumption of extremist content.251 Medical algorithms have been known to misdiagnose US patients,252 and recommend incorrect prescriptions.253 Still, we hand over more control to them, often because they are still as - or more - effective than human decision making, or because they are cheaper."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  45. "Gradual or accumulative loss of control risks can be described as risks resulting from the accumulation of less severe disruptions that gradually weakens systemic resilience until a critical event triggers a catastrophe [12], [127]."

    From Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks (Chin2025)

  46. 68.04.00a · Additional evidence

    Gradual loss of control

    "Risk dimensions • Intent: Unintentional • Competency: Variable • Entity: Variable • Polarity: Multi-agent • Linearity: Non-linear • Reach: Internalized • Order: Variable"

    From Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks (Chin2025)

  47. 72.02.01 · Risk Sub-Category

    Loss of Control Risks

    Passive loss of control

    "...where humans gradually stop exercising meaningful oversight due to automation bias, the AI systems' inherent complexity, or competitive pressures"

    From Frontier AI Risk Management Framework (v1.0) (Tse2025)

  48. 07.04.00 · Risk Category

    Structural

    "Structural risks are concerned with how AI technologies "shape and are shaped by the environments in which they are developed and deployed""

    From Examining the differential risk from high-level artificial intelligence and the question of control (Kilian2023)

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

    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.