Where it hit the plant
raw water intake
chemical dosing
ultrafiltration
dechlorination / UV
reverse osmosis
permeate transfer & backwash
Attack window and detections
Shaded band: the labelled attack window from the iTrust ground-truth catalog. Marks: the first second each engine flagged the window. "No flag" means the engine stayed silent for the whole window.
Why it was flagged
At 2015-12-29 22:55:18, attack #22 (MSMP) manipulated UV401, AIT502, P501 — “Stop UV-401; Value of AIT502 set as 150; Force P-501 to remain on”. The serving model raised the alert immediately — within the first second of the attack (peak score 7.2852x the operating threshold). The dominant physical evidence: P402 — UV/RO feed pump (duty), Stage 4 (dechlorination / UV) was driven to a state the plant's learned physics did not predict from the rest of the process, carrying 20% of the anomaly score — 25x its share in normal operation. Supporting deviations were concentrated in AIT502, AIT402, LIT401. Independently, the mined process rule “PIT503 ≈ 0.7834·PIT501 + -7.309, residual ∈ [-0.7047, 0.6132]” was violated for 466 seconds inside the attack window. The fused detection stack corroborated the alert across channels (physics residual + process rules), which is the platform's high-confidence state. In plain terms: the plant's own physics stopped agreeing with what the sensors were reporting, in exactly the part of the process the attacker touched.
Sensors carrying the anomaly score
| Sensor | Share of score | Deviation | Share vs normal |
|---|---|---|---|
| P402 UV/RO feed pump (duty), Stage 4 (dechlorination / UV) | 20.2% | 49.8σ | 25.0x |
| AIT502 RO feed ORP analyzer, Stage 5 (reverse osmosis) | 15.4% | 43.1σ | 4.8x |
| AIT402 ORP analyzer ahead of dechlorination, Stage 4 (dechlorination / UV) | 15.0% | 41.4σ | 4.7x |
| LIT401 RO feed tank level transmitter, Stage 4 (dechlorination / UV) | 8.0% | 22.3σ | 1.7x |
| P501 RO high-pressure pump, Stage 5 (reverse osmosis) | 5.3% | 13.1σ | 47.3x |
| PIT503 RO reject pressure transmitter, Stage 5 (reverse osmosis) | 5.0% | 13.2σ | 2.3x |
| PIT501 RO feed pressure transmitter, Stage 5 (reverse osmosis) | 4.2% | 10.8σ | 2.0x |
| AIT503 RO feed conductivity analyzer, Stage 5 (reverse osmosis) | 4.0% | 11.1σ | 1.1x |
Process rules violated inside the window
PIT503 ≈ 0.7834·PIT501 + -7.309, residual ∈ [-0.7047, 0.6132]correlation bandviolated for 7m 46sconfidence 99.97%FIT501 ≈ 0.9242·FIT401 + 0.1401, residual ∈ [-0.007591, 0.007749]correlation bandviolated for 7m 36sconfidence 99.95%
Every figure has a run.
2026-06-11T22:34:18Z, commit 97752838a3f3d5271b7e43335fcf1f839fdf057a
sha-97752838a3f3
80c98149b000d88af3fc7b58ab407a24c81f3839426e7d4e53c2011bbf15c52a
2026-06-12T06:42:56Z
2616f67199c281fc558b4b05e3cccdeb223910e4c07addf0c80bc50f0ec5b333
vardar-portal/scripts/build-gallery-data.mjs (DEL-34/DEL-43)
SWaT and WaDi datasets courtesy of iTrust, Centre for Research in Cyber Security, Singapore University of Technology and Design. Detection figures trace to the reproducible model runs shown with each dataset.
The next record is your process.
A technical evaluation on one critical process, with success criteria agreed in advance, produces the only figure that applies to your site.