Engineering safety in machine learning
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives. Therefore, just like for power plants, highways, and myriad other engineered sociotechnical systems, we must consider the safety of systems involving machine learning. In this paper, we first discuss the definition of safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. Then we examine dimensions, such as the choice of cost function and the appropriateness of minimizing the empirical average training cost, along which certain real-world applications may not be completely amenable to the foundational principle of modern statistical machine learning: empirical risk minimization. In particular, we note an emerging dichotomy of applications: ones in which safety is important and risk minimization is not the complete story (we name these Type A applications), and ones in which safety is not so critical and risk minimization is sufficient (we name these Type B applications). Finally, we discuss how four different strategies for achieving safety in engineering (inherently safe design, safety reserves, safe fail, and procedural safeguards) can be mapped to the machine learning context through interpretability and causality of predictive models, objectives beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Certifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Mining with rarity: a unifying framework
Weiss, G. M. (2004) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1007730.1007734 · Cited by 1,393
Benchmarking state-of-the-art classification algorithms for credit scoring: an update of research
Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015) · European Journal of Operational Research · doi:10.1016/j.ejor.2015.05.030 · Cited by 1,284
Wagstaff, K. (2012) · arXiv · doi:10.48550/arxiv.1206.4656 · Cited by 148
Beat the Machine: Challenging Humans to Find a Predictive Model's “Unknown Unknowns”
Attenberg, J., Ipeirotis, P., & Provost, F. (2015) · Journal of Data and Information Quality · doi:10.1145/2700832 · Cited by 103 · cited 1×
“In these pa rts of the space, distance from the decision boundary is fairly meaningless and the typical trigger for the reject option sh ould be avoided [19].”
Background
Cited by
A survey of deep learning techniques for autonomous driving
Grigorescu, S., Trasnea, B., Cocias, T., & Macesanu, G. (2020) · Journal of Field Robotics · doi:10.1002/rob.21918 · Cited by 1,809
Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods
Hüllermeier, E., & Waegeman, W. (2021) · Machine Learning · doi:10.1007/s10994-021-05946-3 · Cited by 1,834
“…of uncertainty is desirable and should be considered as a key feature of any machine learning method, all the more in safety-critical application domains such as medicine (Yang et al., 2009; Lambrou et al., 2011) or sociotechnical systems (Varshney, 2016; Varshney and Alemzadeh, 2016).”
BackgroundArtificial intelligence, bias and clinical safety
Challen, R., Denny, J., Pitt, M., Gompels, L., Edwards, T., & Tsaneva-Atanasova, K. (2019) · BMJ Quality & Safety · doi:10.1136/bmjqs-2018-008370 · Cited by 956
“If the system’s confidence is low, best practice design would be to fail-safe 46 and refuse to make a prediction either way.”
Influential(2016) · neural information processing systems · Cited by 556
Lambert, S. I., Madi, M., Sopka, S., Lenes, A., Stange, H., Buszello, C.-P., & Stephan, A. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00852-5 · Cited by 404
“By consequence, ensuring high-quality input data as well as ensuring that the system is applied to the anticipated patient population is of utmost importance to AI-based systems ’ acceptance 60 .”
Metadata
- Authors
- Varshney, K. R.
- Venue
- 2016 Information Theory and Applications Workshop (ITA)
- Publisher
- IEEE
- Published
- 2016-01
- Pages
- 1-5
- OpenAlex
- W2268946161
- Cited by
- 118
- References
- 6
- FWCI
- 29.51
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Engineering safety in machine learning. https://app.cochat.ai/papers/10.1109/ita.2016.7888195
- The paper
- Varshney, K. R. (2016). Engineering safety in machine learning. 2016 Information Theory and Applications Workshop (ITA). https://doi.org/10.1109/ita.2016.7888195
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.