MIT AI Risk Repository
Browse AI risks
300 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.
-
31.08.00 · Risk Category
"Like manufactured items like soda bottles, mechanized lawnmowers, pharmaceuticals, or cosmetic products, generative AI models can be viewed like a new form of digital products developed by tech companies and deployed widely with the potential to cause harm at scale....Products liability evolved because there was a need to analyze and redress the harms caused by new, mass-produced technological products. The situation facing society as generative AI impacts more people in more ways will be similar to the technological changes that occurred during the twentieth century, with the rise of industr
-
33.03.00 · Risk Category
"Given that generative AI, including ChatGPT, is still evolving, relevant regulations and policies are far from mature. With generative AI creating different forms of content, the copyright of these contents becomes a significant yet complicated issue. Table 3 presents the challenges associated with regulations and policies, which are copyright and governance issues."
-
"Generative AI can create new risks as well as unintended consequences. Different entities such as corporations (Mäntymäki et al., 2022), universities, and governments (Taeihagh, 2021) are facing the challenge of creating and deploying AI governance. To ensure that generative AI functions in a way that benefits society, appropriate governance is crucial. However, AI governance is challenging to implement. First, machine learning systems have opaque algorithms and unpredictable outcomes, which can impede human controllability over AI behavior and create difficulties in assigning liability and a
-
39.10.00 · Risk Category
HLI-based systems such as self-driving drones and vehicles will act autonomously in our world. In these systems, a challenging question is “who is liable when a self-driving system is involved in a crash or failure?”.
-
"Despite the promise of streamlined travel, AI also brings concerns about who is liable in case of accidents and which ethical principles autonomous transportation agents should follow when making decisions with a potentially dangerous impact to humans, for example, in case of an accident."
-
"Despite the promise of streamlined travel, AI also brings concerns about who is liable in case of accidents and which ethical principles autonomous transportation agents should follow when making decisions with a potentially dangerous impact to humans, for example, in case of an accident."
-
"When it causes harm to others the losses caused by the harm will be sustained by the injured victims themselves and not by the manufacturers, operators or users of the system, as appropriate."
-
53.04.04 · Risk Sub-Category
Indirect AI contributions to existential risks
Erosion of international law and global governance architectures;
-
-
55.01.02 · Risk Sub-Category
Risks from accelerating scientific progress
Faster scientific progress makes it harder for governance to keep pace with development
"Exacerbating these problems is that faster scientific progress would make it even harder for governance to keep pace with the deployment of new technologies. When these technologies are especially powerful or dangerous, such as those discussed above, insufficient governance can magnify their harms.8 This is known as the pacing problem, and it is an issue that technology governance already faces [47], for a variety of reasons"
-
"The complex and rapidly evolving nature of AI makes them inherently difficult to govern effectively, leading to systemic regulatory and oversight failures."
-
61.02.12 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Challenges in perceiving, measuring, and recognizing harm
"Harm from AI often manifests subtly or over the long term, making it difficult to identify, measure, and address effectively."
-
"Harms could result from a combination of regulatory, management, and operational failures."
-
61.02.14 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Complex attribution and responsibility
"When multiple actors are involved in AI development and deployment, it becomes difficult to assign responsibility for harm, complicating accountability."
-
61.02.40 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Rapid development outpacing regulation
"The fast pace of AI development may outstrip regulatory and legal frameworks."
-
61.02.41 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Resistance to international law
"AI models and systems may prove difficult to regulate or control under international law."
-
61.02.47 · Risk Sub-Category
Sources of systemic risks from general-purpose AI
Unpredictability of AI development trajectory
"The unpredictable trajectory of AI development complicates governance and risk management."
-
62.16.02 · Risk Sub-Category
General Evaluations (Limited coverage of capabilities evaluations)
"GPAI model developers might run capabilities evaluations to determine whether it has dangerous or dual-use capabilities, and then decide whether it is safe to deploy. Such capabilities evaluations can fail to demonstrate all the capabilities of a model. For example, evaluations may miss certain capabilities that are difficult to assess, prohibitively costly to verify, or obscured by the model’s tendency to refuse responses due to safety training, even if it possesses some of these capabilities."
-
62.16.06 · Risk Sub-Category
General Evaluations (Biased evaluations of encoded human values)
"Encoded human values in AI models that are easier to evaluate might be preferred for inclusion in evaluations over those that are more difficult to measure [13]. This might come at the expense of more desirable but harder-to-quantify values. This bias can lead to an imbalance, where easier-to-measure values dominate the evaluation process, while other important values are underrepresented."
-
62.16.08 · Risk Sub-Category
Benchmarking (Benchmark leakage or data contamination)
"Benchmark leakage [235, 224, 221, 161] can happen when an AI model is trained or fine-tuned with evaluation-related data. This can lead to an unreliable model evaluation, especially if the data contains question-answer pairs from bench- marks."
-
"This type of contamination [170] occurs when the raw and unlabeled data of a benchmark is used as part of the training set. Such data may not be properly formatted and may contain noise, especially if the contamination happens before the data is pre-processed into the benchmark. If this contamination occurs, it could cast doubt on the few-shot and zero-shot performance of the model on that benchmark."
-
"Models that have been trained on data encoded in multiple languages, such as LLMs trained on web-crawled data, may contain contamination that is obscured by translation [226]. The most basic form of this is when a benchmark is trans- lated to another language and then fed to the model as training data. The fact that the benchmark is translated before becoming training data can obscure the contamination from detection methods, giving false assurance that the model has generalized on the capabilities that the benchmark tests for."
-
"Guideline contamination refers to scenarios where instructions for the collec- tion, annotation, or use of the dataset are exposed to the model [170]. These instructions may contain explicit data-label pairs that can improve the model’s capabilities for the task."
-
"Annotation contamination refers to scenarios where the model is exposed to the benchmark labels during training [170]. This type of contamination can make the model learn the acceptable distribution of outputs. Combining this with raw data contamination of the test split, any evaluation made with the benchmark is invalidated because the entire test split is essentially leaked to the model."
-
"Once a model is deployed, it can be exposed to benchmark data provided by the users [95, 170]. The model may then be further trained by these user inputs containing benchmark data."
-
62.16.14 · Risk Sub-Category
Benchmark Inaccuracy (Benchmarks may not accurately evaluate capabilities)
"Benchmarks of AI systems can both underestimate and overestimate the capa- bilities of those AI systems. Underestimates can happen if an evaluation is not comprehensive enough, if the benchmark is saturated by existing models, or if the capabilities in question depend on a complicated setup, such as realistic computer programming tasks. Overestimates of capabilities can occur if an AI system is trained or fine-tuned on the contents of the benchmark, leading to overfitting."
-
"Benchmark saturation refers to benchmarks reaching their evaluation ceiling. The tendency towards benchmark saturation has been demonstrated in various benchmarks [19]. When benchmarks reach or are close to saturation, they stop being effective measures for new models, as more nuanced capability gains might not be detected."
-
62.16.16 · Risk Sub-Category
Benchmark Limitations (Insufficient benchmarks for AI safety evaluation)
"Benchmarks dedicated to measuring the performance of AI systems (e.g., on programming or math tasks) are more well-developed than those for assessing safety and harms in AI systems [234]. This gap can lead to AI systems excelling in specific tasks while exhibiting harmful behaviors that go undetected. More safety-related evaluation datasets can help in identifying previously overlooked undesirable model behaviors."
-
62.16.17 · Risk Sub-Category
Benchmark Limitations (Underestimating capabilities that are not covered by benchmarks)
"A lack of test coverage by benchmarks on specific abilities of a model can obscure the model’s capabilities from both the developer and the user [160]. This can lead to a false sense of safety and trust due to a lack of understanding of the model’s limitations."
-
62.17.00 · Risk Category
-
-
62.17.01 · Risk Sub-Category
Conflicts of interest in auditor selection
"Conflicts of interest can arise if there is no independence in the auditor selection process or if the auditors are closely associated with the developer [123, 157]. In such cases, the conflict of interest can appear even if third-party evaluators are involved. In the case of external auditing, the potential candidates might be selected from a narrow group of auditors, or have conflicting financial incentives for whether to report model shortcomings publicly."
-
"Auditors may not be able to address all of the specific safety, performance, or validation needs. Reports of passing audits may be more inclusive than can be justified due to a lack of knowledge of specific risks and how they can be tested, or a lack of capacity to perform sufficiently rigorous testing."
-
"Auditors may not publicly disclose risks they find, may be required to not pub- licize shortcomings, or may not receive sufficient cooperation from the relevant internal parties."
-
"Without accurate documentation on how a model's data was collected, curated, and used to train a model, it might be harder to satisfactorily explain the behavior of the model with respect to the data."
-
"Data provenance refers to tracing history of data, which includes its ownership, origin, and transformations. Without standardized and established methods for verifying where the data came from, there are no guarantees that the data is the same as the original source and has the correct usage terms."
-
"Determining who is responsible for an AI model is challenging without good documentation and governance processes."
-
"Insufficient documentation of the system that uses the model and the model’s purpose within the system in which it is used."
-
"Testing is unrepresentative when the test inputs are mismatched with the inputs that are expected during deployment."
-
"Since foundation models can be used for many purposes, a model’s intended use is important for defining the relevant risks of that model. As the use changes, the relevant risks might correspondingly change."
-
"Lack of data transparency is due to insufficient documentation of training or tuning dataset details. "
-
"A metric selected to measure or track a risk is incorrectly selected, incompletely measuring the risk, or measuring the wrong risk for the given context."
-
"AI model risks are socio-technical, so their testing needs input from a broad set of disciplines and diverse testing practices."
-
"Determining responsibility when EAI causes harm requires new accountability and liability frameworks that address the complexities of highly autonomous physical systems. Human users may disagree with decisions taken by expert EAI systems, raising significant questions of delegation and responsibility [108]. Lack of EAI accountability could lead to confusion for users and breakdowns in traditional justice systems [109]."
-
"EAI deployment could fundamentally reshape society, particularly if the speed of technological development outpaces society’s ability to adapt [103, 120]. For example, EAI systems could provide physical threats of violence and mass surveillance capabilities to back up AI-enabled authoritarianism [121]."
-
03.06.00 · Risk Category
"At a time of increasing climate urgency, energy consumption and the carbon footprint of AI applications are also matters of ethics and responsibility [68]. As with other energy-intensive technologies like proof-of-work blockchain, the call is to research more environmentally sustainable algorithms to offset the increasing use scale."
-
05.15.00 · Risk Category
Generative models are known for their substantial energy requirements, necessitating significant amounts of electricity, cooling water, and hardware containing rare metals. The extraction and utilization of these resources frequently occur in unsustainable ways. Consequently, papers highlight the urgency of mitigating environmental costs for instance by adopting renewable energy sources and utilizing energy-efficient hardware in the operation and training of generative AI systems.
-
10.09.00 · Risk Category
"The production process of these devices requires raw materials such as nickel, cobalt, and lithium in such high quantities that the Earth may soon no longer be able to sustain them in sufficient quantities."
-
depletion or contamination of natural resources, and damage to built environments... that may occur throughout the lifecycle of digital technologies [170, 237] from “crale (mining) to usage (consumption) to grave (waste)”
-
"The computing power used in training, testing, and deploying generative AI systems, especially large scale systems, uses substantial energy resources and thereby contributes to the global climate crisis by emitting greenhouse gasses."
-
"Impacts at a high-level, from the AI ecosystem to the Earth itself, are necessarily broad but can be broken down into components for evaluation."
-
The risk of harm to the natural environment posed by the ML system.
Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.