A Time-Series Self-Supervised Learning Approach to Detection of Cyber-physical Attacks in Water Distribution Systems

Abstract

Water Distribution System (WDS) threats have significantly grown following the Maroochy shire incident, as evidenced by proofed attacks on water premises. As a result, in addition to traditional solutions (e.g., data encryption and authentication), attack detection is being proposed in WDS to reduce disruption cases. The attack detection system must meet two critical requirements: high accuracy and near real-time detection. This drives us to propose a two-stage detection system that uses self-supervised and unsupervised algorithms to detect Cyber-Physical (CP) attacks. Stage 1 uses heuristic adaptive self-supervised algorithms to achieve near real-time decision-making and detection sensitivity of 66% utilizing Boss. Stage 2 attempts to validate the detection of attacks using an unsupervised algorithm to maintain a detection accuracy of 94% utilizing Isolation Forest. Both stages are examined against time granularity and are empirically analyzed against a variety of performance evaluation indicators. Our findings demonstrate that the algorithms in stage 1 are less favored than those in the literature, but their existence enables near real-time decision-making and detection reliability. In stage 2, the isolation Forest algorithm, in contrast, gives excellent accuracy. As a result, both stages can collaborate to maximize accuracy in a near real-time attack detection system.

A Comprehensive Survey of Machine Learning Methodologies with Emphasis in Water Resources Management

“…Another problem that households have to face is frequent attacks on water supply facilities, because this way, water distribution systems (WDSs) are deregulated [221]. To address this problem, it is proposed that in addition to traditional solutions such as data encryption and authentication, it is proposed to detect attacks on WDSs to reduce the cases of disruption.…”

“…For high accuracy, heuristic adaptive self-predictive algorithms are applied for nearreal-time decision making and detection sensitivity. Unsupervised algorithms attempt to detect the attacks to maintain high detection accuracy as much as possible using isolation forest [221]. Based on the problems mentioned above, the World Health Organization has taken actions on water safety plans (WSPs), which involve holistic assessment and risk assessment.…”

Innovative Water Supply Network Pressure Management Method—The Establishment and Application of the Intelligent Pressure-Regulating Vehicle

“…Since the ultimate goal of pressure management is to reduce network leakage, studies often determine whether a DMA or a zone is necessary for pressure management based on the leakage rate. The minimum night flow method (MNF method) is often used as an important method for network leakage analysis, involving the determination of the minimum night flow and the determination of the legal water consumption of the customer at night, which can yield the night leakage of a DMA or a zone [12]. Cheung [13] through a study of Brazilian water consumption data, concluded that the MNF occurs between 1:00 a.m. and 4:00 a.m.…”

“…In addition, it is very cumbersome to repeat the design and build temporary pressure reduction stations for experiments at different locations. During the field experiment, intelligent pressure-regulating technology was born as a result of the widespread popularity of artificial intelligence [12] and supervisory control and data acquisition (SCADA) [13]. It can gather network operating data in real-time and realize pressure management without influencing customer water consumption.…”

Fake News Detection in Different Applications: State-of-the-art and Future Directions

“…It is possible to address regression-based challenges by producing predictions of stable or actual properties using aspects of easily available information. Surprisingly, the categorization totally isolates each item of data from the perspective of its class labels [22].…”