mlsanityData to 7 Oct 2026

Quantitative AI Risk Assessments: Opportunities and Challenges

arXiv 2209.06317 ↗First posted 13 Sep 2022cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations, litigation, and general societal concerns. As with any promising technology, organizations want to benefit from the positive capabilities of AI technology while reducing the risks. The best way to reduce risks is to implement comprehensive AI lifecycle governance where policies and procedures are described and enforced during the design, development, deployment, and monitoring of an AI system. Although support for comprehensive governance is beginning to emerge, organizations often need to identify the risks of deploying an already-built model without knowledge of how it was constructed or access to its original developers. Such an assessment will quantitatively assess the risks of an existing model in a manner analogous to how a home inspector might assess the risks of an already-built home or a physician might assess overall patient health based on a battery of tests. Several AI risks can be quantified using metrics from the technical community. However, there are numerous issues in deciding how these metrics can be leveraged to create a quantitative AI risk assessment. This paper explores these issues, focusing on the opportunities, challenges, and potential impacts of such an approach, and discussing how it might influence AI regulations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 110 references that are in the map. First posted on arXiv 13 Sep 2022.

Builds on

25 of 110 references.

References · 25

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  8. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  9. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  10. 2019Measurement and Fairnesscited by 299
  11. 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
  12. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
13 more
  1. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  2. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  3. 2020Imitation Attacks and Defenses for Black-box Machine Translation Systemscited by 78
  4. 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 66
  5. 2022Evaluation Gaps in Machine Learning Practicecited by 48
  6. 2022Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learningcited by 47
  7. 2020Accuracy and Fairness Trade-offs in Machine Learning: A Stochastic Multi-Objective Approachcited by 39
  8. 2020The Problem with Metrics is a Fundamental Problem for AIcited by 37
  9. 2018URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detectioncited by 34
  10. 2021What are you optimizing for? Aligning Recommender Systems with Human Valuescited by 28
  11. 2021Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AIcited by 22
  12. 2021FreaAI: Automated extraction of data slices to test machine learning modelscited by 10
  13. 2021Testing Framework for Black-box AI Modelscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.

  1. 2023Model Reporting for Certifiable AI: A Proposal from Merging EU Regulation into AI Developmentcited by 6
  2. 2023Selecting Models based on the Risk of Damage Caused by Adversarial Attackscited by 1
  3. 2023Assessing Trustworthiness of Autonomous Systemscited by 1
  4. 2024On the Conditions for Domain Stability for Machine Learning: a Mathematical Approachcited by 0