MIT AI Risk Repository

Browse AI risks

38 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 DSIT2023 ×

38 entries

  1. "Frontier AI models can contain and magnify biases ingrained in the data they are trained on, reflecting societal and historical inequalities and stereotypes.177 These biases, often subtle and deeply embedded, compromise the equitable and ethical use of AI systems, making it difficult for AI to improve fairness in decisions.178 Removing attributes like race and gender from training data has generally proven ineffective as a remedy for algorithmic bias, as models can infer these attributes from other information such as names, locations, and other seemingly unrelated factors."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  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. 67.03.00 · Risk Category

    Misuse risks

    "Frontier AI may help bad actors to perform cyberattacks, run disinformation campaigns and design biological or chemical weapons. Frontier AI will almost certainly continue to lower the barriers to entry for less sophisticated threat actors.192 We focus here on only a few important misuse risks, but this is not to downplay the importance of others."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  4. 67.03.03 · Risk Sub-Category

    Misuse risks

    Disinformation and Influence Operations

    "In addition to unintentional degradation of the information environment (discussed in the section on Societal Harms above), frontier AI can be misused to deliberately spread false information to create disruption, persuade people on political issues, or cause other forms of harm or damage."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  5. 67.03.01 · Risk Sub-Category

    Misuse risks

    Dual Use Science risks

    "Frontier AI systems have the potential to accelerate advances in the life sciences, from training new scientists to enabling faster scientific workflows. While these capabilities will have tremendous beneficial applications, there is a risk that they can be used for malicious purposes, such as for the development of biological or chemical weapons."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  6. 67.03.02 · Risk Sub-Category

    Misuse risks

    Cyber

    "As the programming abilities of AI systems continue to expand, frontier AI is likely to significantly exacerbate existing cyber risks. Most notably, AI systems can be used by potentially anyone to create faster paced, more effective and larger scale cyber intrusion via tailored phishing methods or replicating malware. Frontier AI’s effect on the overall balance between cyber offence and defence is uncertain, as these tools also have many applications in improving the cybersecurity of systems and defenders are mobilising significant resources to utilise frontier AI for defensive purposes.209 I

    From Capabilities and Risks from Frontier AI (DSIT2023)

  7. 67.04.00 · Risk Category

    Loss of control

    -

    "Humans may increasingly hand over control of important decisions to AI systems, due to economic and geopolitical incentives. Some experts are concerned that future advanced AI systems will seek to increase their own influence and reduce human control, with potentially catastrophic consequences - although this is contested."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  8. 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)

  9. 67.01.02 · Risk Sub-Category

    Societal harms

    Labour market disruption

    "Economists view disruption and displacement in labour markets as one of the risks through which rapid advances in AI may affect citizens and reduce social welfare.170"

    From Capabilities and Risks from Frontier AI (DSIT2023)

  10. 67.04.02 · Risk Sub-Category

    Loss of control

    Future AI systems might actively reduce human control

    "Loss of control could be accelerated if AI systems take actions to increase their own influence and reduce human control. This threat model is controversial - experts in AI significantly disagree on how likely it is and those who deem it is likely disagree on the timeframe."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  11. 67.04.03 · Risk Sub-Category

    Loss of control

    Capabilities that could be used to reduce human control - Manipulation

    "There is evidence that language models tend to respond as though they share the user’s stated views, and larger models do this more than smaller ones.276 The ability to predict people’s views and generate text that they will endorse could be useful for manipulation."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  12. 67.04.04 · Risk Sub-Category

    Loss of control

    Capabilities that could be used to reduce human control - Cyber offence

    "Instead of - or in addition to - manipulating humans, AI systems could acquire influence by exploiting vulnerabilities in computer systems. Offensive cyber capabilities could allow AI systems to gain access to money, computing resources, and critical infrastructure. As discussed earlier in this report, frontier AI is already lowering the barrier for threat actors and future AI agents may be able to execute cyber attacks autonomously.":

    From Capabilities and Risks from Frontier AI (DSIT2023)

  13. 67.04.05 · Risk Sub-Category

    Loss of control

    Capabilities that could be used to reduce human control - Autonomous replication and adaptation

    "Controlling AI systems could become much harder if they could autonomously persist, replicate, and adapt in cyberspace. No current AI systems have this capability, but recent research found that frontier AI agents can perform some relevant tasks.279"

    From Capabilities and Risks from Frontier AI (DSIT2023)

  14. 67.01.00 · Risk Category

    Societal harms

    "There is a wide range of potential societal harms arising from the use of AI.152 This has sparked a debate around the ethics of AI, with a wide proliferation of ethical frameworks and principles.153 We focus here on only a few societal harms, but this is not to downplay the importance of others."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  15. 67.01.01a · Additional evidence

    Societal harms

    Degradation of the information environment

  16. 67.01.01b · Additional evidence

    Societal harms

    Degradation of the information environment

  17. 67.01.01c · Additional evidence

    Societal harms

    Degradation of the information environment

  18. 67.01.01d · Additional evidence

    Societal harms

    Degradation of the information environment

  19. 67.01.02a · Additional evidence

    Societal harms

    Labour market disruption

  20. 67.03.01a · Additional evidence

    Misuse risks

    Dual Use Science risks

    "Frontier AI systems have the potential to accelerate advances in the life sciences, from training new scientists to enabling faster scientific workflows. While these capabilities will have tremendous beneficial applications, there is a risk that they can be used for malicious purposes, such as for the development of biological or chemical weapons."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  21. 67.03.01b · Additional evidence

    Misuse risks

    Dual Use Science risks

    "Frontier AI systems have the potential to accelerate advances in the life sciences, from training new scientists to enabling faster scientific workflows. While these capabilities will have tremendous beneficial applications, there is a risk that they can be used for malicious purposes, such as for the development of biological or chemical weapons."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  22. 67.03.01c · Additional evidence

    Misuse risks

    Dual Use Science risks

    "Frontier AI systems have the potential to accelerate advances in the life sciences, from training new scientists to enabling faster scientific workflows. While these capabilities will have tremendous beneficial applications, there is a risk that they can be used for malicious purposes, such as for the development of biological or chemical weapons."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  23. 67.03.02a · Additional evidence

    Misuse risks

    Cyber

  24. 67.03.02b · Additional evidence

    Misuse risks

    Cyber

  25. 67.03.02c · Additional evidence

    Misuse risks

    Cyber

  26. 67.03.02d · Additional evidence

    Misuse risks

    Cyber

  27. 67.03.03a · Additional evidence

    Misuse risks

    Disinformation and Influence Operations

  28. 67.03.03b · Additional evidence

    Misuse risks

    Disinformation and Influence Operations

  29. 67.04.00a · Additional evidence

    Loss of control

    -

    "Humans may increasingly hand over control of important decisions to AI systems, due to economic and geopolitical incentives. Some experts are concerned that future advanced AI systems will seek to increase their own influence and reduce human control, with potentially catastrophic consequences - although this is contested."

    From Capabilities and Risks from Frontier AI (DSIT2023)

  30. 67.04.01a · Additional evidence

    Loss of control

    Humans might increasingly hand over control to misaligned AI systems

  31. 67.04.02a · Additional evidence

    Loss of control

    Future AI systems might actively reduce human control

  32. 67.04.02b · Additional evidence

    Loss of control

    Future AI systems might actively reduce human control

  33. 67.04.02c · Additional evidence

    Loss of control

    Future AI systems might actively reduce human control

  34. 67.04.02d · Additional evidence

    Loss of control

    Future AI systems might actively reduce human control

  35. 67.04.03a · Additional evidence

    Loss of control

    Capabilities that could be used to reduce human control - Manipulation

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