MIT AI Risk Repository
Browse AI risks
2,500 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.
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
—
-
37.02.04.a · Additional evidence
Attributing the responsibility for AI's failures
—
-
37.02.04.b · Additional evidence
Attributing the responsibility for AI's failures
—
-
"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."
-
44.01.01.a · Additional evidence
Intentional: socially condemned/illegal
AI intentionally designed and used to harm animals in ways that contradict social values or are illegal
—
-
44.01.02.a · Additional evidence
Intentional: socially condemned/illegal
AI designed to benefit animals, humans, or ecosystems is intentionally abused to harm animals in ways that contradict social values or are illegal
—
-
44.02.00.a · Additional evidence
—
-
44.02.00.b · Additional evidence
—
-
44.03.01.a · Additional evidence
AI is designed in a way that shows ignorant, reckless, or prejudiced lack of consideration for its impact on animals
—
-
44.03.01.b · Additional evidence
AI is designed in a way that shows ignorant, reckless, or prejudiced lack of consideration for its impact on animals
—
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.