# Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure

DevFeed: [Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure](<https://devfeed.tech/articles/physics-attested-federated-learning-securing-collaborative-anomaly-detection-in-critical-water-infrastructure-119891.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.34804>)

Author: Jeff Nijsse, Shu Su, Benjamin Oholeguy, Sreenivas Sremath Tirumala

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [Physics-guided deep learning](<https://devfeed.tech/topics/physics-guided-deep-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [admission](<https://devfeed.tech/tags/admission.md>), [adversary](<https://devfeed.tech/tags/adversary.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [anomaly-detection](<https://devfeed.tech/tags/anomaly-detection.md>), [attack](<https://devfeed.tech/tags/attack.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [channel](<https://devfeed.tech/tags/channel.md>), [clients](<https://devfeed.tech/tags/clients.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [detection](<https://devfeed.tech/tags/detection.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [physics](<https://devfeed.tech/tags/physics.md>), [water](<https://devfeed.tech/tags/water.md>)

## AI overview

The paper uses physical process invariants, mined from clean operational data, as an admission gate for federated intrusion detection updates, aiming to catch poisoned telemetry that update-space defenses cannot distinguish from honest contributions. Across SWaT, WADI, and BATADAL, the gate rejected no honest shards among 25 except cross-channel fabrications on SWaT and BATADAL, including perturbations admitted by FoolsGold. On SWaT telemetry, five invariants detected 12 of 35 attacks and nine detected 20. With nine invariants, the gate recovered 78% of targeted-attack recall lost to replay poisoning across five standard aggregators (95% CI 57-97%; p < 0.001 over 20 seeds), and 82% under FedAvg. The authors also show clients can prove batch compliance with zk-SNARKs without revealing telemetry. These are reported benchmark results; the abstract does not establish performance beyond the evaluated settings.

## Source excerpt

arXiv:2609.34804v2 Announce Type: replace Abstract: Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. However, existing defences operate strictly in update space, leaving aggregators blind to data poisoning; model updates derived from fabricated telemetry remain indistinguishable from honest contributions. We repurpose process invariants, physical relations that always hold in normal operation, such as conservation of mass, from runtime detection heuristics into a verifiable admission requirement for federated updates, mined automatically from clean operational data. We evaluate this admission gate across two physical water testbeds (SWaT, WADI) and a distribution benchmark (BATADAL), testing seven aggregation rules against telemetry fabrication, exposure-only replay poisoning, and an invariant-aware adaptive adversary. Across three testbeds the mined invariants reject none of 25 honest shards except every cross-channel fabrication on SWaT and BATADAL, including optimised perturbations that the similarity based FoolsGold admits in full. On real telemetry, five mined invariants detect 12 of SWaT's 35 attacks, while nine invariants detect 20. With nine invariants, the admission gate removes 78% of the targeted-attack recall lost to replay poisoning (95% CI 57--97%, $p < 0.001$ over 20 seeds) across five standard aggregators, and 82% under FedAvg. To reconcile physical admission control with federated data privacy, we show invariant compliance using zero-knowledge proofs (zk-SNARKs) to allow clients to prove batch adherence without revealing operational telemetry.