Papers › SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical...

SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure

27 May 2020arXiv:2005.13166archive 2025-07-28

Koorosh Aslansefat, Ioannis Sorokos, Declan Whiting, Ramin Tavakoli Kolagari, Yiannis Papadopoulos

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behaviour and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using distributional shift detection measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that the approach can provide a basis for detecting whether the application context of an ML component is valid in the safety-security. Our preliminary code and results are available at https://github.com/ISorokos/SafeML.

PaperPDFCode

Code

ISorokos/SafeML officialmentioned in papermentioned on GitHub report
n-akram/SafeML mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BIG-bench Machine LearningDomain AdaptationGeneral ClassificationImage ClassificationIntrusion DetectionSafe Exploration

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
General Classification XOR KNN Accuracy 93.1045 #1 of 4 Archive leaderboard report
General Classification XOR RF Accuracy 92.962 #2 of 4 Archive leaderboard report
General Classification XOR CART Accuracy 92.8179 #3 of 4 Archive leaderboard report
General Classification XOR LDA Accuracy 77.2217 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Dense ConnectionsFeedforward NetworkGaussian ProcessSVM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections