MIT AI Risk Repository
Browse AI risks
494 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.
-
"Personal health deterioration - Physical deterioration of an individual or animal over time, increasing their risk of disease, organ failure, prolonged hospital stay or death, etc."
-
"Property damage - Action(s) that lead directly or indirectly to the damage or destruction of tangible property eg. buildings, possessions, vehicles, robots."
-
58.03.00 · Risk Category
"Psychological - Direct or indirect impairment of the emotional and psychological mental health of an individual, organisation, or society."
—
-
"Anxiety/depression - Mental health decline due to addiction, negative social interactions such as humiliation and shaming and traumatic distressing events such as online violence or rape."
-
"Trauma - Severe and lasting emotional shock and pain caused by an extremely upsetting experience."
-
58.04.00 · Risk Category
"Reputational - Damage to the reputation of an individual, group or organisation."
-
"Loss of confidence/trust - Misleading or unfair change(s) in how an individual, group, or organisation is viewed, leading to loss of ability to conduct relationships, raise capital, recruit people, etc."
-
"Financial/earnings loss - Loss of money, income or value due to the use or misuse of a technology system."
-
"Opportunity loss - Loss of ability to take advantage of a financial or other opportunity, such as education, employability/securing a job."
-
58.06.00 · Risk Category
"Human Rights and Civil Liberties - Use or misuse of a technology system in a manner that compromises fundamental human rights and freedoms."
-
"Benefits/entitlements loss - Denial or or loss of access to welfare benefits, pensions, housing, etc due to the malfunction, use or abuse of a technology system."
-
"Dignity loss - Perceived loss of value experienced by or disrespect shown to an individual or group, resulting in self-sheltering, loss of connections and relationships, and public stigmatisation."
-
"Breach of ethics/values/norms - An actual or perceived violation or deviation from the established societal values, norms or ethical standards or principles."
-
"Critical infrastructure damage - Damage, disruption to or destruction of systems essential to the functioning and safety of a nation or state, including energy, transport, health, finance, and communication systems."
-
"In contrast to technical AI hazards, socio-technical hazards also require hu- man input related to social and cultural aspects [45]. Human judgment must be employed when deciding on quantification and treatment methods. For instance, AI hazards concerning discrimination and privacy, which are abstract concepts lacking a uniform technical definition, further complicate a clear quantification of the associated risks. Although quantitative methods exist to assess and treat these AI hazards, they require coordination with social and cultural values [27]."
-
"The third axis of the taxonomy pertains to the level, which differentiates between the AI application and system levels, as they are defined in Section 3. Allocating an AI hazard to its level helps to determine the level at which an action is required. This consequently sets the basis for who is supposed to act."
-
"For instance, the main person responsible for an AI hazard manifesting on the AI system level would be the AI developer, whereas an AI hazard affecting the whole AI application requires a more diverse group, including domain experts."
-
"For instance, the main person responsible for an AI hazard manifesting on the AI system level would be the AI developer, whereas an AI hazard affecting the whole AI application requires a more diverse group, including domain experts."
-
"The large-scale erosion or violation of fundamental human rights and freedoms."
-
62.01.00 · Risk Category
—
-
"Risks can be realized by intentional or unintentional actions, and in some cases the intent is difficult to establish. To manage these risks, rigorous evaluations and red teaming can be performed, guardrails can be put in place, and model release can be gradual, such that AI model malfunctions have either low likeli- hood or low probability of occurrence. To prevent intentional misuse, acceptable use policies can be in place, and for riskier models Know Your Customer (KYC) measures can also be implemented by model providers."
-
"In the context of Normal Accident Theory [150], normal accidents are those that “could no longer be ascribed to isolated equipment malfunction, operator error, or acts of God.” We refer to these as “system failures” (to be distinguished from “systemic risks”), while the opposite would be “isolated failures.” For isolated failures, harms are consistent with the underlying failure modes. For example, an AI capable of producing false or misleading content would constitute risks re- lated to misinformation and disinformation. Whereas for system failures, harms are not consistent with the underlyi
-
"In the context of Normal Accident Theory [150], normal accidents are those that “could no longer be ascribed to isolated equipment malfunction, operator error, or acts of God.” We refer to these as “system failures” (to be distinguished from “systemic risks”), while the opposite would be “isolated failures.” For isolated failures, harms are consistent with the underlying failure modes. For example, an AI capable of producing false or misleading content would constitute risks re- lated to misinformation and disinformation. Whereas for system failures, harms are not consistent with the underlyi
-
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.01 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Supervised/unsupervised AI (AI data quality related - biased training data)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.02 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Supervised/unsupervised AI (AI training performance related - Robustness)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.03 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Supervised/unsupervised AI (AI training performance related - Accuracy)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.04 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Supervised/unsupervised AI (AI training performance related - Reliability)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.05 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Reinforcement learning AI (Training design related)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.04.06 · Risk Sub-Category
Dimension - Technical Attributes (AI inadequacy - technical failure)
Reinforcement learning AI (Training performance related)
"As above, there are broadly two dimensions of technical failure modes: quality of data or input signal, and training performance. Due to a lack of transparency, it may be difficult to ascertain the type of technical failure that gives rise to a particular risk, and it is often a combination of several factors. Risks pertain- ing to AI failures are exacerbated by poor quality training data and imperfect training signals. Various measures can be implemented to improve the quality of the training data, and fine-tuning techniques can be used to disincentivize harmful model behavior."
-
62.05.00 · Risk Category
"An example of AI capabilities is that an AI might be capable of developing novel bioweapons. Whereas an example of AI inadequacy is a self-driving car causing an accident due to not being able to recognize certain objects. The boundary between capabilities and inadequacy is sometimes blurred. For exam- ple, when an AI generates falsehoods, it could be framed as either a capability of developing fiction, or an inadequacy in generating truthful content."
-
"Inherent capabilities are inherent to the AI, whether they are deliberately trained or have emerged unintentionally."
-
62.14.00 · Risk Category
-
-
62.16.00 · Risk Category
"This section catalogs the risk sources and risk management measures related to model evaluations (often called evals). We categorize them into the fol- lowing groups: general evaluations, benchmarking, red teaming, auditing, and interpretability/explainability. The subsection on general evaluations consists of items that are common to various evaluation techniques, while the other subsections are specific to their respective evaluation types."
-
62.27.00 · Risk Category
-
-
"An actual or perceived violation or deviation from the established societal values, norms or ethical standards or principles"
-
"Loss of money, income or value due to the use, misuse, or underperformance of a genAI application"
-
"AI systems leaking, reproducing, generating or inferring sensitive, private, hazardous, or secured information"
-
"Physical injury to an individual or group, or damage to physical property due to the use of misuse of a technology system or set of systems"
-
"Accidental or deliberate loss of life, including suicide, extinction or cessation, due to the use or misuse of a technology system"
-
"Physical pain, injury, illness, or disease suffered by an individual or group due to the malfunction, use or misuse of a technology system."
-
"Physical deterioration of an individual or animal over time in the form of disease, organ failure, prolonged hospital stay or death, etc"
-
"Damage to the environment caused by the use or misuse of a technology system or set of systems"
-
67.01.00 · Risk Category
"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."
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.