Anomaly Detection in Cyber Physical Systems Using Recurrent Neural Networks
By Jonathan Goh, Sridhar Adepu, Marcus Tan, Zi Shan Lee. IEEE International Symposium on High-Assurance Systems Engineering, 2017
379 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing
View Paper: https://www.semanticscholar.org/paper/228b4e4bce405c6ecb401a07b8912a0cb9d62668
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ahmed Abdulaal
- Tomer Lancewicki
- Zhuanghua Liu
- Asaf Shabtai
- Moshe Kravchik
- Jonathan Goh
- Min Chen
- Giancarlo Fortino
In Computer Networks and Communications
- Asaf Shabtai
- Moshe Kravchik
- See-Kiong Ng
- Dacheng Chen
- Dan Li
- Ahmed Abdulaal
- Tomer Lancewicki
- Zhuanghua Liu
In Signal Processing
- Asaf Shabtai
- Moshe Kravchik
- See-Kiong Ng
- Dacheng Chen
- Dan Li
- Ahmed Abdulaal
- Tomer Lancewicki
- Zhuanghua Liu
Citations in the corpus
- Deep Learning for Time Series Anomaly Detection: A Survey (2022, neutral): “LSTM-PRED [66] utilises three LSTM stacks with 100 hidden units each, processing data sequences of 100 seconds to learn temporal dependencies.”
- Smart Anomaly Detection in Sensor Systems (2020, methodology): “[61] designed a time series predictor using RNN and used a Cumulative Sum method to identify the anomalies in a cyberphysical system.”
- Detecting Cyber Attacks in Industrial Control Systems Using Convolutional Neural Networks (2018, methodology): “in [7] build a three layer LSTM-RNN model that was trained on the data from the first stage of the SWaT dataset.”
- Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series (2018, methodology): “he anomaly detection performance for both the univariate and multivariate cases. In the univariate case, we compare the performance against the CUSUM approach which was used in previous works such as [41]. For the multivariate case, we compare GAN-AD against PCA-based unsupervised detection by inspe”
- Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization (2021, methodology): “For example, cybersecurity attacks [10, 16] or an internal code bug, which could result in service downtime, immediate tangible business losses, and intangible losses from the loss of customer trust, if not detected and remediated promptly.”
- MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks (2019, background): “ith networked sensors and actuators that generate substantial amounts of multivariate time series data that can be used to continuously monitor the CPS’ working conditions to detect anomalies in time [1] so that the operators can take actions to investigate and resolve the underlying issues. The ubi”