Papers for

water infrastructure operators

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Physics attested federated learning secures water system anomaly detection

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

Abstract: Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. However, existing defenses operate strictly in update space, leaving aggregators blind to data poisoning; model updates derived from fabricated telemetry remain indistinguishable from honest contributions. We repurpose cyber-physical process invariants, such as conservation laws and actuator couplings, 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 100 honest shards and all naively fabricated ones, including optimised perturbations that FoolsGold admits in full. On real telemetry, five mined invariants detect 12 of SWaT's 35 attacks, while nine invariants detect 20, with no honest shard rejected. With nine rules, the physics gate recovers 69--100% of the targeted-attack recall lost to replay poisoning, and 54--100% of that lost to fabricated telemetry, across five standard aggregators. 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.

Mon 28 SeptCryptography and SecurityMachine Learning
The gist
Detecting attacks on critical water systems is important but sharing data between operators risks privacy. The authors show how to use the natural physical laws and rules governing water systems to check if data updates are genuine without revealing sensitive information. This approach blocks fake or poisoned data during collaborative machine learning, improving security in water network monitoring. They tested this method on real water system datasets and found it effectively detects attacks while keeping honest data safe.
Open → 2609.34804v1

Cross-domain method improves industrial control system threat validation

XPhysICS: Cross-Physical-Domain Threat Grounding for Industrial Control Systems Security

Abstract: Industrial control system (ICS) threats documented for one plant can express cyber-physical effects relevant to another, but semantic similarity alone does not establish whether those effects are structurally admissible or evaluable on a target. We present XPhysICS, a provenance-aware, target-conditioned method that separates analyst-guided source abstraction from deterministic grounding into target-specific validation slices. Given a fixed source abstraction, vocabulary and schema, and machine-validated target contract, XPhysICS evaluates candidate mappings using five eligibility criteria: role compatibility, implemented type compatibility, stage coherence, slice viability, and rule-surface applicability. Grounding acceptance, slice adequacy, dynamic realizability, consumer applicability, and consumer outcome remain distinct evidence layers. We evaluate 83 structured source-threat abstractions across water treatment, water distribution, hydro/water-energy, and chemical-process targets. Controlled target-side studies of SWaT-to-water-treatment and WADI-to-water-distribution groundings produce clean, nominal-confounded, and near-threshold consumer outcomes; nine Hydro/GRFICS cases extend bounded validation-slice execution. We also evaluate bounded predictive, state-aware, and phase-aware consumer lanes, the unmodified upstream GeCo implementation, and a paper-derived reproduction of a physics-guided search method over three frozen groundings. Results show that cross-domain ICS threat reuse requires traceable source semantics, explicit target-conditioned grounding criteria, and careful separation of subsequent target-side evidence.

Fri 25 SeptCryptography and SecurityArtificial Intelligence
The gist
Industrial control systems like water treatment plants face cyber-physical threats that can affect multiple types of systems. The authors present XPhysICS, a new method to check if threat patterns identified in one system can be meaningfully applied and tested in another. Their method uses clear rules to decide which threats can be safely transferred between different industrial setups, helping analysts understand risks better across various plants. They tested XPhysICS on several kinds of water and energy systems and showed it supports careful and traceable threat evaluation across different environments.
Open → 2609.30805v1