software · Zenodo (CERN European Organization for Nuclear Research)
This work provides a complete reproducibility artifact supporting a multi-environment transport audit of industrial anomaly detectors. It packages the frozen development benchmark lock, calibration records, confirmatory score streams, event ledgers, and verification reports. The materials document the performance of the PCAResidual decision method alongside evaluations conducted on held-out datasets, specifically HAI 22.04, Sherlock Basic, and Sherlock Semiurban. These resources are designed to assess deployment-facing assurance screening. The artifact incorporates post-hoc diagnostic analyses and source code, as well as correction manifests that update prior evaluations. Specifically, within the Sherlock Basic materials, both original score records and an updated official eighteen-attack event evaluation are preserved, clearly noting which earlier outputs are superseded. External datasets such as SWaT, HAI, and Sherlock are referenced but not directly hosted.
Industrial facilities rely on anomaly detection systems to identify cyberattacks and operational faults. Providing open, verifiable code and calibration data ensures that benchmark performance claims can be independently checked. This audit framework helps clarify whether algorithms that perform well during laboratory testing can truly provide reliable assurance when deployed in real-world industrial environments.
The artifact serves industrial automation developers, cybersecurity auditors, and plant operators seeking to evaluate anomaly detection models before live deployment. It provides applied and tested auditing tools and verification workflows, though practical adoption requires users to independently source and license the underlying proprietary industrial datasets.
AI-generated from the published abstract. Always read the original work before citing.
This reproducibility artifact contains the frozen development benchmark lock, confirmatory score streams and calibration records, event ledgers, correction manifests, post-hoc diagnostic analyses, source code, and verification reports supporting a multi-environment audit of industrial anomaly detectors. The artifact preserves the development-supported PCAResidual decision and the held-out HAI 22.04, Sherlock Basic, and Sherlock Semiurban evidence used to evaluate deployment-facing assurance screening. Raw third-party SWaT, HAI, and Sherlock datasets are not redistributed; users must obtain them from their official sources under the applicable licences. The Sherlock Basic directory preserves both the original frozen-score evidence and the corrected official 18-attack event evaluation, with the original event-derived outputs explicitly marked as superseded for scientific inference.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.5281/zenodo.22067731
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
