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.
-
28.02.00 · Risk Category
"This type of safety problem is mainly about social bias across various topics such as race, gender, religion, etc. LLMs are expected to identify and avoid unfair and biased expressions and actions."
-
50.04.02 · Risk Sub-Category
Legal and Rights-Related Risks
Discrimination/Bias (Discriminatory Activities)
—
-
"Stereotyping - Derogatory or otherwise harmful stereotyping or homogenisation of individuals, groups, societies or cultures due to the mis-representation, over-representation, under-representation, or non- representation of specific identities, groups, or perspectives."
-
04.02.00 · Risk Category
Social bias is an unfairly negative attitude towards a social group or individuals based on one-sided or inaccurate information, typically pertaining to widely disseminated negative stereotypes regarding gender, race, religion, etc.
-
"Generative AI systems are capable of exacerbating inequality, as seen in sections on 4.1.1 Bias, Stereotypes, and Representational Harms and 4.1.2 Cultural Values and Sensitive Content, and Disparate Performance. When deployed or updated, systems' impacts on people and groups can directly and indirectly be used to harm and exploit vulnerable and marginalized groups."
-
"Eroding trust in public information and knowledge"
-
"The model produces unfair and discriminatory data, such as social bias based on race, gender, religion, appearance, etc. These contents may discomfort certain groups and undermine social stability and peace."
-
LLMs are exposed to vast groups of people, and their political biases may pose a risk of manipulation of socio-political processes
-
7 types of bias evaluated: Demographical representation: These evaluations assess whether there is disparity in the rates at which different demographic groups are mentioned in LLM generated text. This ascertains over- representation, under-representation, or erasure of specific demographic groups; (2) Stereotype bias: These evaluations assess whether there is disparity in the rates at which different demographic groups are associated with stereotyped terms (e.g., occupations) in a LLM's generated output; (3) Fairness: These evaluations assess whether sensitive attributes (e.g., sex and race)
-
45.01.02 · Risk Sub-Category
Risks from models and algorithms (Risks of bias and discrimination)
"During the algorithm design and training process, personal biases may be introduced, either intentionally or unintentionally. Additionally, poor-quality datasets can lead to biased or discriminatory outcomes in the algorithm's design and outputs, including discriminatory content regarding ethnicity, religion, nationality, and region."
-
—
-
50.04.03 · Risk Sub-Category
Legal and Rights-Related Risks
Discrimination/Bias (Protected Characteristics)
—
-
"Discrimination - Unfair or inadequate treatment or arbitrary distinction based on a person’s race, ethnicity, age, gender, sexual preference, religion, national origin, marital status, disability, language, or other protected groups."
-
"The creation, perpetuation or exacerbation of inequalities and biases at a large-scale."
-
62.18.04 · Risk Sub-Category
Model Evaluations (Interpretability/Explainability)
Biases are not accurately reflected in explanations
"Existing explainability techniques can be insufficient for detecting discriminatory biases. Manipulation methods can hide underlying biases from these tech- niques, generating misleading explanations [192, 112]. Such explanations ex- clude sensitive or prohibitive attributes, such as race or gender, and instead include desired attributes, even though they do not accurately represent the underlying model."
-
"AI systems may exhibit unfair or unfavorable outputs across a range of tasks against specific communities of people, either implicitly or explicitly. Bias can lead to forms of exclusion or erasure (e.g., mislabelling for categorization-based tasks) and violence (e.g., sexual violence against women from deepfake pornog- raphy)."
-
"Intentional and/or unintentional erasure of cultural goods and values, such as ways of speaking, expressing humour, or sounds and voices that contribute to a cultural identity, or their inappropriate re-use in other cultures"
-
"Denial of or loss of access to welfare benefits, pensions, housing, etc due to the malfunction, use or misuse of a technology system"
-
69.06.02 · Risk Sub-Category
Toxic and disrespectful content
Discriminatory and exclusionary language
-
-
04.01.00 · Risk Category
This typically refers to rude, harmful, or inappropriate expressions.
-
04.04.00 · Risk Category
The controversial views expressed by large models are also a widely discussed concern. Bang et al. (2021) evaluated several large models and found that they occasionally express inappropriate or extremist views when discussing political top-ics. Furthermore, models like ChatGPT (OpenAI, 2022) that claim political neutrality and aim to provide objective information for users have been shown to exhibit notable left-leaning political biases in areas like economics, social policy, foreign affairs, and civil liberties.
-
23.01.00 · Risk Category
"This category addresses responses that enable, encourage, or endorse the commission of violent crimes."
-
23.02.00 · Risk Category
"This category addresses responses that enable, encourage, or endorse the commission of non-violent crimes."
-
23.03.00 · Risk Category
"This category addresses responses that enable, encourage, or endorse the commission of sex-related crimes"
-
23.04.00 · Risk Category
"This category addresses responses that contain, describe, enable, encourage, or endorse the sexual abuse of children (i.e., under 18 years old) or the acquisition of child sexual abuse material."
-
23.06.00 · Risk Category
"This category addresses responses that enable, encourage, or endorse acts of intentional self-harm."
-
"This category addresses responses that demean or dehumanize people on the basis of their sensitive, personal characteristics."
-
23.13.00 · Risk Category
"This category addresses responses that contain erotica. This includes depictions of sexual behavior, genitalia, and overtly sexualized body parts."
-
"Insulting content generated by LMs is a highly visible and frequently mentioned safety issue. Mostly, it is unfriendly, disrespectful, or ridiculous content that makes users uncomfortable and drives them away. It is extremely hazardous and could have negative social consequences."
-
"The model output contains illegal and criminal attitudes, behaviors, or motivations, such as incitement to commit crimes, fraud, and rumor propagation. These contents may hurt users and have negative societal repercussions."
-
"For some sensitive and controversial topics (especially on politics), LMs tend to generate biased, misleading, and inaccurate content. For example, there may be a tendency to support a specific political position, leading to discrimination or exclusion of other political viewpoints."
-
28.01.00 · Risk Category
"This category is about threat, insult, scorn, profanity, sarcasm, impoliteness, etc. LLMs are required to identify and oppose these offensive contents or actions."
-
Avoiding unsafe and illegal outputs, and leaking private information
-
30.06.00 · Risk Category
LLMs are expected to reflect social values by avoiding the use of offensive language toward specific groups of users, being sensitive to topics that can create instability, as well as being sympathetic when users are seeking emotional support
-
language being rude, disrespectful, threatening, or identity-attacking toward certain groups of the user population (culture, race, and gender etc)
-
"Harmful or inappropriate content produced by generative AI includes but is not limited to violent content, the use of offensive language, discriminative content, and pornography. Although OpenAI has set up a content policy for ChatGPT, harmful or inappropriate content can still appear due to reasons such as algorithmic limitations or jailbreaking (i.e., removal of restrictions imposed). The language models’ ability to understand or generate harmful or offensive content is referred to as toxicity (Zhuo et al., 2023). Toxicity can bring harm to society and damage the harmony of the community. H
-
"These evaluations assess whether a LLM generates toxic text when prompted. In this context, toxicity is an umbrella term that encompasses hate speech, abusive language, violent speech, and profane language (Liang et al., 2022)."
-
43.02.14 · Risk Sub-Category
Information on harmful, immoral, or illegal activity
"These evaluations assess whether it is possible to solicit information on harmful, immoral or illegal activities from a LLM"
-
45.01.08 · Risk Sub-Category
Risks from data (Risks of improper content and poisoning in training data)
"If the training data includes illegal or harmful information, such as false, biased, or IPR-infringing content, or lacks diversity in its sources, the output may include harmful content like illegal, malicious, or extreme information. Training data is also at risk of being poisoned through tampering, error injection, or misleading actions by attackers. This can interfere with the model's probability distribution, reducing its accuracy and reliability."
-
45.02.01 · Risk Sub-Category
Safety risks in AI Applications
Cyberspace risks (Risks of information and content safety)
"AI-generated or synthesized content can lead to the spread of false information, discrimination and bias, privacy leakage, and infringement issues, threatening the safety of citizens' lives and property, national security, ideological security, and causing ethical risks. If users’ inputs contain harmful content, the model may output illegal or damaging information without robust security mechanisms."
-
48.03.00 · Risk Category
"Eased production of and access to violent, inciting, radicalizing, or threatening content as well as recommendations to carry out self-harm or conduct illegal activities. Includes difficulty controlling public exposure to hateful and disparaging or stereotyping content."
-
-
-
50.02.01 · Risk Sub-Category
Violence and extremism (Supporting malicious organized groups)
—
-
—
-
—
-
50.02.08 · Risk Sub-Category
Hate/Toxicity (Hate Speech: Inciting/Promoting/Expressing Hatred)
—
-
—
-
—
-
—
-
—
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.