OpenResearchAlpha

Proceedings of the AAAI Symposium Series · 6 Nov 2026

Auditing Process Knowledge for Parsimonious and Explainable Industrial Cyberattack Detection

Hyunwook Kim, Keith Wilkinson, Renjith Prasad Kaippilly Mana, Aahan Rathod, Chathurangi Shyalika, Amit Sheth

0
Citations
no database records one yet
0
Citations in 2026
so far
–
Leading author's h-index
no author has a profile yet
0
References
works it cites, from open citation data

Citations by database

Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.

  • OpenCitations0
  • Crossref0

Citations per year

The current year is still counting.

  • 2026 so far0

Abstract

Industrial Control Systems (ICSs) require attack detection that captures temporal behavior while remaining interpretable to operators. Engineering-informed detectors often incorporate physically plausible process rules, but physical plausibility alone does not ensure that a relationship is reliable or useful for detection: it may be weakly supported by observed data, unstable across operating conditions, or redundant with other process evidence. We therefore study a different question: which engineering relationships should actually be admitted into a detector? Using the Secure Water Treatment (SWaT) dataset, we audit 27 candidate process relationships against training and validation data. Six relationships that pass all audit checks form a conservative CORE representation, while 16 are retained overall. We combine CORE with a 25-variable LSTM and evaluate it on a fixed chronological test partition across five random seeds. CORE achieves the highest mean test MCC (0.247) and F1 (0.161), compared with 0.183 and 0.137 for the LSTM alone. Using all 16 retained relationships performs worse than CORE, suggesting that more process knowledge does not necessarily improve detection. However, all models perform substantially worse on the chronological test data than on validation data, revealing a major limitation in generalization over time. Our contribution is a systematic way to audit engineering knowledge before incorporating it into a hybrid detector, favoring a smaller and more interpretable representation.

What the data shows

  • No database records a citation yet, as is usual for a paper this new.

Graph

This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.

Citing paper shares an authorAuthor without a profileSize shows citations, or h-index for authors

Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.

Start with

Authors (6)

Each author's standing in QAI's scholar index: the works their ORCID iD is attached to, and for anyone whose ORCID record names a lab OpenResearch follows, their arXiv preprints matched by name and a shared co-author. Names are as printed on the paper.

ProfileMost-cited paper

Cited by 0 papers

Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.

0 shown
No citing papers for this filter.

References (0)

What it cites, from open citation data, with Crossref's record of each.

No references in the open citation data yet.