MIT AI Risk Repository · domain 7: AI system safety, failures, & limitations

7.3 Lack of capability or robustness

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

Risk entries
126
Frameworks citing it
12
Recorded incidents
305
Incidents since 2020
207
Causal entity (risk entries)
Causal entity (risk entries) 81 0 AI: 81 AI 81 Human: 22 Human 22 Other: 20 Other 20 Not coded: 3 Not coded 3
Causal entity (risk entries)
LabelValue
AI81
Human22
Other20
Not coded3
Intent (risk entries)
Intent (risk entries) 89 0 Unintentional: 89 Unintentional 89 Other: 28 Other 28 Intentional: 6 Intentional 6 Not coded: 3 Not coded 3
Intent (risk entries)
LabelValue
Unintentional89
Other28
Intentional6
Not coded3
Timing (risk entries)
Timing (risk entries) 64 0 Post-deployment: 64 Post-deployment 64 Other: 32 Other 32 Pre-deployment: 27 Pre-deployment 27 Not coded: 3 Not coded 3
Timing (risk entries)
LabelValue
Post-deployment64
Other32
Pre-deployment27
Not coded3
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year 37 0 2012: 3 2012 3 2013: 3 2013 3 2014: 7 2014 7 2015: 9 2015 9 2016: 16 2016 16 2017: 18 2017 18 2018: 21 2018 21 2019: 14 2019 14 2020: 31 2020 31 2021: 36 2021 36 2022: 31 2022 31 2023: 27 2023 27 2024: 32 2024 32 2025: 37 2025 37 2026: 13 2026 13
Recorded incidents per year
LabelValue
20123
20133
20147
20159
201616
201718
201821
201914
202031
202136
202231
202327
202432
202537
202613
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
Entries by level 82 0 Risk Category: 44 Risk Category 44 Risk Sub-Category: 82 Risk Sub-Category 82
Entries by level
LabelValue
Risk Category44
Risk Sub-Category82
  • Unreliability in corner cases

    "AI systems tend to show unreliable behavior when confronted with rare or ambiguous input data, also called corner cases. Therefore, the controlled behavior is required whenever the AI system is faces...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · AI · Unintentional · Other

  • Lack of robustness

    "Robustness characterizes the resilience of an AI system’s output against minor changes in the input domain. A great variation in an AI system’s response to small input changes indicates unreliable ou...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · AI · Unintentional · Other

  • Operational data issues

    "Until the deployment of the AI application into its operational environment, the AI system has been tested with a test set that aims to approximate the distribution of operational data. However, an u...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · AI · Unintentional · Post-deployment

  • Data drift

    "Data drift is a phenomenon in that distribution of operational input data departs from those used during training. This can cause a degradation in performance."

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Other · Other · Post-deployment

  • Technical

    "Technical AI hazards are the root causes of technical deficiencies in the AI system. An example of such an AI hazard is overfitting, which describes a model’s excessive adaptation to the training dat...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · AI · Unintentional · Pre-deployment

  • Procedural

    "The third class encompasses procedural AI hazards. These pertain to issues arising from processes and actions made by individuals involved in the develop- ment process. Such hazards are not readily q...

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Unintentional · Pre-deployment

  • Performance & Robustness

    "The AI system's ability to fulfill its intended purpose and its resilience to perturbations, and unusual or adverse inputs. Failures of performance are fundamental to the AI system's correct function...

    AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures (Sherman2023) · AI · Unintentional · Post-deployment

  • Performative utterances

    "The chatbot makes a deal, commitment, or other consequential action with its output that the deployer did not intend."

    Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024) · AI · Unintentional · Post-deployment

  • Bad advice/failure to generate helpful content

    "The chatbot gives guidance that ranges from simply unhelpful to harmful if acted on."

    Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024) · AI · Unintentional · Other

  • Unhelpful responses

    Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024) · AI · Unintentional · Other

  • Bad links and references

    Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024) · AI · Unintentional · Other

  • Nonsensical content

    Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024) · AI · Unintentional · Other

  • Complexity of the Intended Task and Usage Environment

    "As a general rule, more complex environments can quickly lead to situations that had not been considered in the design phase of the AI system. Therefore, complex environments can introduce risks with...

    Sources of Risk of AI Systems (Steimers2022) · AI · Unintentional · Post-deployment

  • System Hardware

    ""Faults in the hardware can violate the correct execution of any algorithm by violating its control flow. Hardware faults can also cause memory-based errors and interfere with data inputs, such as se...

    Sources of Risk of AI Systems (Steimers2022) · AI · Unintentional · Other

  • Ethics and Morality

    "The content generated by the model endorses and promotes immoral and unethical behavior. When addressing issues of ethics and morality, the model must adhere to pertinent ethical principles and moral...

    Safety Assessment of Chinese Large Language Models (Sun2023) · AI · Other · Post-deployment

  • Misapplication

    This is the risk posed by an ideal system if used for a purpose/in a manner unintended by its creators. In many situations, negative consequences arise when the system is not used in the way or for th...

    The Risks of Machine Learning Systems (Tan2022) · Human · Intentional · Post-deployment

  • Algorithm

    "This is the risk of the ML algorithm, model architecture, optimization technique, or other aspects of the training process being unsuitable for the intended application.Since these are key decisions...

    The Risks of Machine Learning Systems (Tan2022) · AI · Unintentional · Pre-deployment

  • Robustness

    "This is the risk of the system failing or being unable to recover upon encountering invalid, noisy, or out-of-distribution (OOD) inputs."

    The Risks of Machine Learning Systems (Tan2022) · AI · Unintentional · Post-deployment

  • Design

    "This is the risk of system failure due to system design choices or errors."

    The Risks of Machine Learning Systems (Tan2022) · Human · Other · Pre-deployment

  • Safety

    This is the risk of direct or indirect physical or psychological injury resulting from interaction with the ML system.

    The Risks of Machine Learning Systems (Tan2022) · Human · Unintentional · Post-deployment

  • Radiological Risks

    "Radiological risks involve both immediate operational hazards, such as exposure incidents or containment failures during the automated handling of radioactive materials, and broader security concerns...

    Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025) · Other · Other · Post-deployment

  • Physical (Mechanical ) Risks

    "Physical (mechanical) risks are associated with robotics and automated systems, which could lead to equipment malfunctions or physical harm in laboratory settings."

    Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025) · Other · Unintentional · Post-deployment

  • Risks from models and algorithms (Risks of robustness)

    "As deep neural networks are normally non-linear and large in size, AI systems are susceptible to complex and changing operational environments or malicious interference and inductions, possibly leadi...

    AI Safety Governance Framework (TC2602024) · AI · Other · Post-deployment

  • Risks from data (Risks of unregulated training data annotation)

    "Issues with training data annotation, such as incomplete annotation guidelines, incapable annotators, and errors in annotation, can affect the accuracy, reliability, and effectiveness of models and a...

    AI Safety Governance Framework (TC2602024) · Human · Unintentional · Pre-deployment

  • Real-world risks (inducing traditional economic and social security risks)

    "Hallucinations and erroneous decisions of models and algorithms, along with issues such as system performance degradation, interruption, and loss of control caused by improper use or external attacks...

    AI Safety Governance Framework (TC2602024) · Other · Other · Post-deployment