SWaT: a water treatment testbed for research and training on ICS security

By Aditya P. Mathur, Nils Ole Tippenhauer. 2016 International Workshop on Cyber-physical Systems for Smart Water Networks (CySWater), 2016

958 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Control and Systems Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/818a236f573431aab50969cde4ced8b3d48a1deb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Control and Systems Engineering

In Hardware and Architecture

Citations in the corpus

MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks (2019, background): “1 SWaT The Secure Water Treatment (SWaT) system is an operational test-bed for water treatment that represents a small-scale version of a large modern water treatment plant found in large cities [25].”
WADI: a water distribution testbed for research in the design of secure cyber physical systems (2017, background): “One innate property of the design of WADI is its connectivity to the SWaT testbed [6].”
Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network (2020, background): “Each record is labeled as either normal or attack; (iv) Secure Water Treatment ( SWaT ) data [18], which is collected from a water treatment testbed over 11 days.”
Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding (2021, methodology): “SWaT [21] (Secure Water Treatment) and WADI [19] (Water Distribution) are two datasets about water treatment plants, which have been used for MTS anomaly detection in [19].”
Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series (2018, background): “ment System The Secure Water Treatment (SWaT) system is an operational test-bed for water treatment that represents a small-scale version of a large modern water treatment plant found in large cities [39] 3. The water puriﬁcation process in SWaT is composed of six sub-processes referred to as P1 thr”
USAD: UnSupervised Anomaly Detection on Multivariate Time Series (2020, methodology): “The collected dataset [13] consists of 11 days of continuous operation: 7 days collected under normal operations and 4 days collected with attack scenarios.”
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines (2021, methodology): “In this regard, several real-world datasets (e.g., SWaT and WADI) have been released [57], [58] so that researchers can use them without the need to collect vast numbers of data personally.”
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT (2021, methodology): “SWaT [55] The Secure Water Treatment dataset is collected from a water treatment testbed for cyber-attack investigation initially launched in May 2015.”
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection (2023, background): “(5) SWaT (Secure Water Treatment) is a 51-dimension sensor-based dataset collected from critical infrastructure systems under continuous operations [47].”
ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis (2024, methodology): “For anomaly detection, we compare models on ﬁve widely-used benchmarks: SMD (Su et al., 2019), SWaT (Mathur & Tippenhauer, 2016), PSM (Abdulaal et al., 2021), MSL and SMAP (Hundman et al., 2018).”
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series (2021, methodology): “The Secure Water Treatment (SWaT) dataset comes from a water treatment test-bed coordinated by Singapore’s Public Utility Board (Mathur and Tippenhauer 2016).”
Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization (2021, background): “Fourth, with 70 features, this dataset is significantly larger in dimensionality than other datasets, except for the dataset in [20], which proved to be particularly challenging for the benchmark models against classical machine learning approaches [2].”
FITS: Modeling Time Series with 10k Parameters (2023, methodology): “We use five commonly used benchmark datasets: SMD (Server Machine Dataset (Su et al., 2019)), PSM (Polled Server Metrics (Abdulaal et al., 2021)), SWaT (Secure Water Treatment (Mathur & Tippenhauer, 2016)), MSL (Mars Science Laboratory rover), and SMAP (Soil Moisture Active Passive satellite) (Hundm”
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy (2021, background): “(4) SWaT (Secure Water Treatment, Mathur & Tippenhauer (2016)) is obtained from 51 sensors of the critical infrastructure system under continuous operations.”