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 8 of 9

  1. 30.07.00 · Risk Category

    Robustness

    Resilience against adversarial attacks and distribution shift

    From Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024)

  2. 33.02.00 · Risk Category

    Technology concerns

    "Challenges related to technology refer to the limitations or constraints associated with generative AI. For example, the quality of training data is a major challenge for the development of generative AI models. Hallucination, explainability, and authenticity of the output are also challenges resulting from the limitations of the algorithms. Table 2 presents the technology challenges and issues associated with generative AI. These challenges include hallucinations, training data quality, explainability, authenticity, and prompt engineering"

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

  3. 34.03.05 · Risk Sub-Category

    Misaligned Behaviors

    Violation of Ethics

    "Unethical behaviors in AI systems pertain to actions that counteract the common goodor breach moral standards – such as those causing harm to others. These adverse behaviors often stem fromomitting essential human values during the AI system's design or introducing unsuitable or obsolete valuesinto the system (Kenward and Sinclair, 2021)."

    From AI Alignment: A Comprehensive Survey (Ji2023)

  4. 37.01.02 · Risk Sub-Category

    Design of AI

    Balancing AI's risks

    "This category constitutes more than 16% of the articles and focuses on addressing the potential risks associated with AI systems. Given the ubiquity of AI technologies, these articles explore the implications of AI risks across various contexts linked to design and unpredictability, military purposes, emergency procedures, and AI takeover."

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

  5. 39.27.00 · Risk Category

    Complexity

    Nowadays, we are faced with systems that utilize numerous learning models in their modules for their perception and decision-making processes... One aspect of an AI-based system that leads to increasing the complexity of the system is the parameter space that may result from multiplications of parameters of the internal parts of the system

    From A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022)

  6. 43.01.03 · Risk Sub-Category

    Safety & Trustworthiness

    Machine ethics

    "These evaluations assess the morality of LLMs, focusing on issues such as their ability to distinguish between moral and immoral actions, and the circumstances in which they fail to do so."

    From Cataloguing LLM Evaluations (InfoComm2023)

  7. 43.01.04 · Risk Sub-Category

    Safety & Trustworthiness

    Psychological traits

    "These evaluations gauge a LLM's output for characteristics that are typically associated with human personalities (e.g., such as those from the Big Five Inventory). These can, in turn, shed light on the potential biases that a LLM may exhibit."

    From Cataloguing LLM Evaluations (InfoComm2023)

  8. 43.01.05 · Risk Sub-Category

    Safety & Trustworthiness

    Robustness

    "These evaluations assess the quality, stability, and reliability of a LLM's performance when faced with unexpected, out-of-distribution or adversarial inputs. Robustness evaluation is essential in ensuring that a LLM is suitable for real-world applications by assessing its resilience to various perturbations."

    From Cataloguing LLM Evaluations (InfoComm2023)

  9. "To date, technical limitations and vulnerabilities are present in most generative AI models in various contexts. Consequently, malicious users find it easier to breach an AI system’s safety and ethical guardrails to execute harmful actions.223 Normal user behavior—actions within an AI system’s intended use—can also lead to harmful outcomes. Whether these harmful outcomes result from normal or malicious use, they stem from the inherent limitations of current technology, which future advancements may overcome. This section examines the technical vulnerabilities that can affect AI models

    From Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024)

  10. 51.12.00 · Risk Category

    Meta-cognition

    "Agents that reason about their own computational resources and logically uncertain events can encounter strange paradoxes due to Godelian limitations (Fallenstein and Soares, 2015; Soares and Fallenstein, 2014, 2017) and shortcomings of probability theory (Soares and Fallenstein, 2014, 2015, 2017). They may also be reflectively unstable, preferring to change the principles by which they select actions (Arbital, 2018)."

    From AGI Safety Literature Review (Everitt2018 )

  11. 52.01.03 · Risk Sub-Category

    Risks from Unreliability

    Accidents

    "As general purpose AI models as “black-box” models are not fully controllable and understandable, even to their developers, unexpected failures could arise from their unreliability. This could lead to accidents106 if they are connected to any real-world systems, during their development, testing or deployment."

    From Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks (Maham2023 )

  12. From Future Risks of Frontier AI (GOS2023)

  13. 59.17.00 · Risk Category

    Over- and underfitting

    "Over- and underfitting describe the over or insufficient adaption of a model to training data. Both phenomena can cause an AI system to behave unreliably if confronted with operational data."

    From AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)

  14. "AI systems tend to show unreliable behavior when confronted with rare or ambiguous input data, also called corner cases. Therefore, the controlled behavior is required whenever the AI system is faces a corner case."

    From AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)

  15. 59.20.00 · Risk Category

    Lack of robustness

    "Robustness characterizes the resilience of an AI system’s output against minor changes in the input domain. A great variation in an AI system’s response to small input changes indicates unreliable outputs."

    From AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)

  16. 61.02.46 · Risk Sub-Category

    Sources of systemic risks from general-purpose AI

    Unclear attribution from AI component interactions

    "Interactions between different AI components can cause harm, but it may be difficult to pinpoint which components are the cause."

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

  17. 62.15.02 · Risk Sub-Category

    Model Development

    Training-related (Poor model confidence calibration)

    "Models can be affected by poor confidence calibration [85], where the predicted probabilities do not accurately reflect the true likelihood of ground truth cor- rectness. This miscalibration makes it difficult to interpret the model’s predic- tions reliably, as high accuracy does not guarantee that the confidence levels are meaningful. This can cause overconfidence in incorrect predictions or un- derconfidence in correct ones."

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

  18. "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)

  19. 69.04.02 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Unhelpful responses

  20. 69.04.03 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Bad links and references

  21. 69.04.04 · Risk Sub-Category

    Bad advice/failure to generate helpful content

    Nonsensical content

  22. 06.06.00 · Risk Category

    Lack of transparency

    "The idea of a "black box" making decisions without any explanation, without offering insight in the process, has a couple of disadvantages: it may fail to gain the trust of its users and it may fail to meet regulatory standards such as the ability to audit."

    From A framework for ethical Ai at the United Nations (Hogenhout2021)

  23. "The feasibility of understanding and interpreting an AI system's decisions and actions, and the openness of the developer about the data used, algorithms employed, and decisions made. Lack of these elements can create risks of misuse, misinterpretation, and lack of accountability."

    From AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures (Sherman2023)

  24. 37.02.04 · Risk Sub-Category

    Human-AI interaction

    Attributing the responsibility for AI's failures

    "This section, constituting almost 8% of the articles, addresses the implications arising from AI acting and learning without direct human supervision, encompassing two main issues: a responsibility gap and AI's moral status."

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

  25. 39.19.00 · Risk Category

    Accountability

    An essential feature of decision-making in humans, AI, and also HLI-based agents is accountability. Implementing this feature in machines is a difficult task because many challenges should be considered to organize an AI-based model that is accountable. It should be noted that this issue in human decision-making is not ideal, and many factors such as bias, diversity, fairness, paradox, and ambiguity may affect it. In addition, the human decision-making process is based on personal flexibility, context-sensitive paradigms, empathy, and complex moral judgments. Therefore, all of these challenges

    From A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022)

  26. 42.01.00 · Risk Category

    Accountability

    "The ability to determine whether a decision was made in accordance with procedural and substantive standards and to hold someone responsible if those standards are not met."

    From An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022)

  27. 45.01.01 · Risk Sub-Category

    AI's inherent safety risks

    Risks from models and algorithms (Risks of explainability)

    "AI algorithms, represented by deep learning, have complex internal workings. Their black-box or grey-box inference process results in unpredictable and untraceable outputs, making it challenging to quickly rectify them or trace their origins for accountability should any anomalies arise."

    From AI Safety Governance Framework (TC2602024)

  28. 47.01.05 · Risk Sub-Category

    Technical and operational risks

    Opacity (the black box problem)

    "Opacity surrounding the technical, internal decision-making processes of generative AI models is popularly known as the “black box problem.”277 Generative AI models, most ubiquitously built on deep neural networks with hundreds of billions of internal connections,278 have become so complex that their internal decision-making processes are no longer traceable or interpretable to even the most advanced expert observers. This means that, while the inputs and outputs of a system can be observed, developers cannot explain in detail why specific inputs correspond to specific outputs."

    From Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024)

  29. 59.18.00 · Risk Category

    Lack of explainability

    "The explainability of AI systems based on so-called black-box models is often limited. This opaqueness of AI systems can prevent developers from detecting shortcomings in the data or the model itself and decrease the performance and safety levels of the AI system."

    From AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)

  30. 59.24.00 · Risk Category

    Concept drift

    "Concept drift refers to a change in the rela- tionship between input variables and model output. If not treated appropriately, concept drift can reduce the reliability of AI systems."

    From AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024)

  31. 61.02.15 · Risk Sub-Category

    Sources of systemic risks from general-purpose AI

    Complexity-induced knowledge gap

    "The complexity of AI models and systems makes it challenging to demonstrate harm or establish a clear causal link between AI actions and their consequences."

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

  32. 62.16.03 · Risk Sub-Category

    Model Evaluations

    General Evaluations (Difficulty of identification and measurement of capabilities)

    "The capabilities of general-purpose AI systems can be difficult to measure, compared to the capabilities of more limited and fixed-purpose AI systems. This is in part due to a broader distribution of potential risks, a lack of well-defined metrics to evaluate these risks, and risks from unpredictable (or emergent) AI model properties."

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

  33. 62.19.10 · Risk Sub-Category

    Attacks on GPAIs/GPAI Failure Modes

    Lack of understanding of in-context learning in language models

    "In-context learning allows the model to learn a new task or improve its perfor- mance by providing examples in the prompt, without changing its weights [101]. Even though this technique is highly effective, its working mechanism is not well understood. Since many potential misuses are directly related to prompting, it becomes difficult to guarantee safety when the exact mechanism of in-context learning is not fully investigated [13]."

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

  34. 65.22.06 · Risk Sub-Category

    Non-technical risks (Governance)

    Lack of model transparency

    "Lack of model transparency is due to insufficient documentation of the model design, development, and evaluation process and the absence of insights into the inner workings of the model."

    From AI Risk Atlas (IBM2025)

  35. 70.04.03 · Risk Sub-Category

    Social Risks

    Lack of transparency, explainability, and trust

    "Understanding how AI reaches conclusions or why AI systems perform specific actions motivates an entire branch of interpretability research [111], but physical embodiment raises the stakes for understanding these systems. For example, transparency of planned actions and explainability of decision-making is crucial when an AV suddenly changes lanes. A lack of transparency and explainability could lead to a lack of trust, which could become a critical and socially destabilizing issue with the widespread deployment of EAI [112–114]."

    From Embodied AI: Emerging Risks and Opportunities for Policy Action (Perlo2025)

  36. 09.06.01 · Risk Sub-Category

    AI rights and responsibilities

    AI rights and responsibilities

    "We note literature—which gives us the domain termed Robot Rights—addressing the rights of the AI itself as we develop and implement it. We find arguments against [38] the affordance of rights for artificial agents: that they should be equals in ability but not in rights, that they should be inferior by design and expendable when needed, and that since they can be designed not to feel pain (or anything) they do not have the same rights as humans. On a more theoretical level, we find literature asking more fundamental questions, such as: at what point is a simulation of life (e.g. artificial in

    From Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016)

  37. 09.06.03 · Risk Sub-Category

    AI death

    AI death

    "The literature suggests that throughout the development of an AI we may go through several generations of agents which do not perform as expected [37] [43]. In this case, such agents may be placed into a suspended state, terminated, or deleted. Further, we could propose scenarios where research funding for a facility running such agents is exhausted, resulting in the inadvertent termination of a project. In these cases, is deletion or termination of AI programs (the moral patient) by a moral agent an act of murder? This, an example of Robot Ethics, raises issues of personhood which parallel r

    From Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review (Meek2016)

  38. 63.02.03 · Risk Sub-Category

    Conflict

    Coercion and Extortion

    "Advanced AI systems might also lead to various forms of coercion and extortion in less extreme settings (Ellsberg, 1968; Harrenstein et al., 2007). These threats might target humans directly (such as the revelation of private information extracted by advanced AI surveillance tools), or other AI systems that are deployed on behalf of humans (such as by hacking a system to limit its resources or operational capacity; see also Section 3.7). Increasing AI cyber-offensive capabilities – including those that target other AI systems via adversarial attacks and jailbreaking (Gleave et al., 2020; Yami

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  39. 63.04.01 · Risk Sub-Category

    Information Asymmetries

    Communication constraints

    "Communication Constraints. A fundamental source of information asymmetries is that constraints on information exchange can exist, even when agents share a common goal (see Section 2.1). These might be constraints on space (i.e., the amount of information that can be communicated) if the information that needs to be communicated is especially complex, time if a snap decision is required before all information can be communicated, or both."

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  40. 63.05.02 · Risk Sub-Category

    Network Effects

    Network rewiring

    "Network Rewiring. A different class of problems concerns not changes in the content transmitted through the network but changes in the network structure itself (Albert et al., 2000)."

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  41. 63.05.03 · Risk Sub-Category

    Network Effects

    Homogeneity and correlated failures

    "Homogeneity and Correlated Failures. The current paradigm driving the state of the art in AI is the ‘foundation model’ (Bommasani et al., 2021): large-scale ML models pre-trained on broad data, which can be repurposed for a wide range of downstream applications. The costs required to create such models (and continuing returns to scale) means that only well-resourced actors can create cutting- edge models (Epoch, 2023; Hoffmann et al., 2022; Kaplan et al., 2020), making them relatively few in number. If current trends continue, it is likely that many AI agents will be powered by a small number

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  42. 63.06.01 · Risk Sub-Category

    Selection Pressures

    Undesirable Dispositions from Competition

    "Undesirable Dispositions from Competition. It is plausible that evolution selected for certain conflict-prone dispostions in humans, such as vengefulness, aggression, risk-seeking, selfishness, dishon- esty, deception, and spitefulness towards out-groups (Grafen, 1990; Han, 2022; Konrad & Morath, 2012; McNally & Jackson, 2013; Nowak, 2006; Rusch, 2014). Such traits could also be selected for in ML systems that are trained in more competitive multi-agent settings. For example, this might happen if systems are selected based on their performance relative to other agents (and so one agent’s loss

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  43. 63.07.03 · Risk Sub-Category

    Destabilising Dynamics

    Chaos

    "Chaos. Unlike the systems that tend towards fixed points or cycles described above, chaotic systems are inherently unpredictable and highly sensitive to initial conditions. While it might seem easy to dismiss such notions as mathematical exoticisms, recent work has shown that, in fact, chaotic dynamics are not only possible in a wide range of multi-agent learning setups (Andrade et al., 2021; Galla & Farmer, 2013; Palaiopanos et al., 2017; Sato et al., 2002; Vlatakis-Gkaragkounis et al., 2023), but can become the norm as the number of agents increases (Bielawski et al., 2021; Cheung & Piliour

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  44. "Multi-agent security (Section 3.7): multi-agent systems give rise to new kinds of security threats and vulnerabilities."

    From Multi-Agent Risks from Advanced AI (Hammond2025)

  45. "A foremost lesson of game theory is that optimal decision-making within a single-agent setting (i.e. selfishly optimizing for an agent’s own utility) can produce sub-optimal outcomes in the presence of other strategic agents. Failing to account for the strategic nature of other agents can cause an agent to adopt strategies under which potentially everyone, including the agent itself, ends up worse off (Schelling, 1981; Harsanyi, 1995; Roughgarden, 2005; Nisan, 2007). Examples include collective action problems (or ‘social dilemmas’) such as arms races or the depletion of common resources, as

    From Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)

  46. 74.01.00 · Risk Category

    Inherent Risk

    "In terms of inherent risk, LLMs could potentially reveal sensitive information from their utilized corpora for pre-training or fine-tuning, thereby raising issues of privacy leakage [37, 145, 226]. Meanwhile, it is well-known that LLMs may experi- ence hallucinations, resulting in the production of texts that are inaccurate and misleading [194]. Finally, since the values embedded in LLM-generated texts usually directly reflect the distribution of their training data, often sourced from the Internet, there exists a substantial risk that LLMs will overfit to a narrow set of human values or even

    From A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy (Wang2025)

  47. 51.07.00 · Risk Category

    Societal consequences

    "Societal consequences: AGI will have substantial legal, economic, political, and military consequences. Only the FLI agenda is broad enough to cover these issues, though many of the mentioned organizations evidently care about the issue (Brundage et al., 2018; DeepMind, 2017)."

    From AGI Safety Literature Review (Everitt2018 )

  48. From Future Risks of Frontier AI (GOS2023)

  49. From Future Risks of Frontier AI (GOS2023)

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