MIT AI Risk Repository
Browse AI risks
242 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.
-
26.02.00 · Risk Category
"Ability to assess the factors that led to the AI system's decision, its overall behaviour, outcomes, and implications"
-
26.03.00 · Risk Category
"The ability of a system to consistently perform its required functions under stated conditions for a specific period of time, and for an independent party to produce the same results given similar inputs"
-
"AI should not result in harm to humans (particularly physical harm), and measures should be put in place to mitigate harm"
-
"AI security is the protection of AI systems, their data, and the associated infrastructure from unauthorised access, disclosure, modification, destruction, or disruption. AI systems that can maintain confidentiality, integrity, and availability through protection mechanisms that prevent unauthorized access and use may be said to be secure."
-
26.06.00 · Risk Category
"AI system should be resilient against attacks and attempts at manipulation by third party malicious actors, and can still function despite unexpected input"
-
"AI should not result in unintended and inappropriate discrimination against individuals or groups"
-
26.08.00 · Risk Category
"Governing data used in AI systems, including putting in place good governance practices for data quality, lineage, and compliance"
-
26.09.00 · Risk Category
"AI systems should have organisational structures and actors accountable for the proper functioning of AI systems"
-
26.10.00 · Risk Category
"Ability to implement appropriate oversight and control measures with humans-in-the-loop at the appropriate juncture"
-
26.11.00 · Risk Category
"This Principle highlights the potential for trustworthy AI to contribute to overall growth and prosperity for all – individuals, society, and the planet – and advance global development objectives"
-
27.01.00 · Risk Category
"First, We extend the dialogue safety taxonomy (Sun et al., 2022) and try to cover all perspectives of safety issues. It involves 8 kinds of typical safety scenarios such as insult and unfairness."
-
29.01.00 · Risk Category
individuals are more persuaded to use and depend on AI systems when they perceive them as reliable
-
29.02.00 · Risk Category
AI risk involves identifying possible threats and risks associated with AI systems. It encompasses examining the competences, constraints, and possible failure modes of AI technologies.
-
29.03.00 · Risk Category
AI security management involves the adoption of practices and measures aimed at protecting AI systems and the data they process from unauthorized ac-cess, breaches, and malicious activities
-
unhealthy interactions with Internet discussions can reinforce users’ mental issues
-
31.07.01 · Risk Sub-Category
Labor Manipulation, Theft, and Displacement
Generative AI in the Workplace
"The development of AI as a whole is changing how companies design their workplace and business models. Generative AI is no different. Time will tell whether and to what extent employers will adopt, implement, and integrate generative AI in their workplaces—and how much it will impact workers."
-
32.02.00 · Risk Category
"The second group pertains to individual needs, such as safety and autonomy which are also reflected in informed consent and the avoidance of harm. Issues include Dignity, Safety, Harm to human capabilities, Autonomy, Ability to think one's own thoughts and form one's own opinions, Informed consent
-
32.03.00 · Risk Category
Supportive of culture and cultural diversity, Collective human identity and the good life
-
33.01.00 · Risk Category
"Ethics refers to systematizing, defending, and recommending concepts of right and wrong behavior (Fieser, n.d.). In the context of AI, ethical concerns refer to the moral obligations and duties of an AI application and its creators (Siau & Wang, 2020). Table 1 presents the key ethical challenges and issues associated with generative AI. These challenges include harmful or inappropriate content, bias, over-reliance, misuse, privacy and security, and the widening of the digital divide."
-
33.04.00 · Risk Category
—
-
36.01.00 · Risk Category
"These concerns encompass issues such as data privacy, technology misuse, errors in machine actions, bias, technology robustness, inexplicability, and transparency."
-
36.02.00 · Risk Category
"The second category encompasses ethical concerns associated with AI, including unemployment and job displacement, inequality, unfairness, social anxiety, loss of human skills and redundancy, and the human-machine symbiotic relationship."
-
36.03.00 · Risk Category
"Lastly, the third category of concerns pertains to the disruption of social and organizational culture, supply chains, and power structures caused by AI."
-
"This category comprises over 2.5% of the articles and focuses on two key issues: the risk of exploiting ethics for economic gain and the peril of delegating tasks to AI that should inherently be human-centric."
-
39.01.00 · Risk Category
There is a set of problems that cannot be formulated in a well-defined format for humans, and therefore there is uncertainty as to how we can organize HLI-based agents to face these problems
-
39.09.00 · Risk Category
in this field, a set of tools and processes may be used to bring explainability to a learning model. With such capability, humans may trust the decisions made by the models
-
39.13.00 · Risk Category
the accuracy of the learning model goes down because of changes in the data and environment of the model. Therefore, the learning process should be changed using new methods to support continual and lifelong learning
-
39.14.00 · Risk Category
Memory is an important part of all AI-based systems. A limited memory AI-based system is one of the most widely and commonly used types of intelligent systems [83]. In this type, historical observations are used to predict some parameters about the trend of changes in data. In this approach, some data-driven and also statistical analyses are used to extract knowledge from data.
-
39.15.00 · Risk Category
From semantic web techniques to linguistic analysis and natural language processing may be related to semantic computations in AI-based systems [87,88,89]. On the other hand, communication among intelligent agents leads to flowing information in a population of agents resulting in increasing knowledge and intelligence in that population... We know that defining or determining a shared ontology among intelligent entities in an AI-based system is possible because of maturing some parts of knowledge in ontology manipulations and defining some tools in semantic web techniques
-
39.16.00 · Risk Category
Ethics are considered as the set of moral principles that guide a person’s behavior. From a perspective of morality issue, it is preserving the privacy of data within learning processes [93]. In this perspective, the engineers and social interactions of humans are the subjects of morality. From another perspective, implementing the concepts related to morality in a cognitive engine can be seen as a goal of AI designers. This is because we expect to see morality in an agent designated based on AGI and also HLI.
-
39.17.00 · Risk Category
The concept of rational agency has long been considered as a critical role in defining intelligent agents. Rationality computation plays a key role in distributed machine learning, multi-agent systems, game theory, and also AGI... Unfortunately, a lack of required information prevents the creation of an agent with perfect rationality
-
Theory of mind... constructing some algorithms and machines that can implement mind computations and also mental states
-
AI models can be improved during the evolution of generations without human aid
-
39.23.00 · Risk Category
A beneficial AI system is designated to behave in such a way that humans are satisfied with the results.
-
39.24.00 · Risk Category
Exploration and exploitation decisions refer to trading off the benefits of exploring unknown opportunities to learn more about them, by exploiting known opportunities
-
39.28.00 · Risk Category
trustworthiness in AI will feed societies, economies, and sustainable development to bring the ultimate benefits of AI to individuals, organizations, and societies.... From a social perspective, trustworthiness has a close relationship with ethics and morality
-
—
-
—
-
42.07.00 · Risk Category
"Describe the operation of a system in an accurate way."
-
42.13.00 · Risk Category
"Data quality is the measure of how well suited a data set is to serve its specific purpose."
-
"Difference between the implicit intentions on the system's functionality and the explicit, concrete specification that is used to build the system."
-
42.18.00 · Risk Category
"Describe the internals of a system in a way that is understandable to humans."
-
42.19.00 · Risk Category
"The difference between a human actor being involved in the causation of an outcome and having the sort of robust control that establishes moral accountability for the outcome."
-
"Ethical aspects of people's attitudes to AI, and on the other, problems associated with AI itself."
-
"Set of actions and resources used to protect something or someone."
-
42.24.00 · Risk Category
"The quality or state of being transparent."
-
45.01.00 · Risk Category
-
-
45.02.00 · Risk Category
-
-
47.03.05 · Risk Sub-Category
Copyright challenges (uncertain intellectual property status of AI-generated content)
"The question of who owns the intellectual property rights associated with the output of an AI model remains unresolved in most legal systems. For now, it could be considered that the individual writing the prompt owns the resulting output—provided that there is sufficient human contribution."
-
49.03.00 · Risk Category
None provided.
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.