Federated Variational Learning for Anomaly Detection in Multivariate Time Series

@article{Zhang2021FederatedVL,
  title={Federated Variational Learning for Anomaly Detection in Multivariate Time Series},
  author={Kai Zhang and Yushan Jiang and Lee M. Seversky and Chengtao Xu and Dahai Liu and Houbing Herbert Song},
  journal={2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)},
  year={2021},
  pages={1-9}
}
  • Kai Zhang, Yushan Jiang, H. Song
  • Published 18 August 2021
  • Computer Science
  • 2021 IEEE International Performance, Computing, and Communications Conference (IPCCC)
Anomaly detection has been a challenging task given high-dimensional multivariate time series data generated by networked sensors and actuators in Cyber-Physical Systems (CPS). Besides the highly nonlinear, complex, and dynamic nature of such time series, the lack of labeled data impedes data exploitation in a supervised manner and thus prevents an accurate detection of abnormal phenomenons. On the other hand, the collected data at the edge of the network is often privacy sensitive and large in… 

Figures and Tables from this paper

Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Data
TLDR
This paper proposes FedDPMS (Federated Differentially Private Means Sharing), an FL algorithm in which clients deploy variational auto-encoders to augment local datasets with data synthesized using differentially private means of latent data representations communicated by a trusted server.
FedHarmony: Unlearning Scanner Bias with Distributed Data
TLDR
It is shown that to remove the scanner-specific effects, the proposed FedHarmony framework only need to share the mean and standard deviation of the learned features, helping to protect individual subjects’ privacy.

References

SHOWING 1-10 OF 34 REFERENCES
MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
TLDR
The proposed MAD-GAN framework considers the entire variable set concurrently to capture the latent interactions amongst the variables and is effective in reporting anomalies caused by various cyber-intrusions compared in these complex real-world systems.
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series
TLDR
Experiments show that this approach detects anomalies more accurately than baseline approaches, accurately captures correlations between sensors, and allows users to deduce the root cause of a detected anomaly.
Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
TLDR
GTA, a new framework for multivariate time-series anomaly detection that involves automatically learning a graph structure, graph convolution, and modeling temporal dependency using a transformer-based architecture, is presented.
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
TLDR
The core idea is to capture the normal patterns of multivariate time series by learning their robust representations with key techniques such as stochastic variable connection and planar normalizing flow, reconstruct input data by the representations, and use the reconstruction probabilities to determine anomalies.
USAD: UnSupervised Anomaly Detection on Multivariate Time Series
TLDR
A fast and stable method called UnSupervised Anomaly Detection for multivariate time series (USAD) based on adversely trained autoencoders capable of learning in an unsupervised way is proposed.
Deep Anomaly Detection for Time-Series Data in Industrial IoT: A Communication-Efficient On-Device Federated Learning Approach
TLDR
A new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT and an attention mechanism-based convolutional neural network-long short-term memory (AMCNN-LSTM) model to accurately detect anomalies is proposed.
Multivariate Time-series Anomaly Detection via Graph Attention Network
TLDR
This paper proposes a novel self-supervised framework for multivariate time-series anomaly detection that outperforms other state-of-the-art models on three real-world datasets and has good interpretability and is useful for anomaly diagnosis.
Multi-Task Network Anomaly Detection using Federated Learning
TLDR
This paper proposes a multi-task deep neural network in federated learning (MT-DNN-FL) to perform network anomaly detection task, VPN (Tor) traffic recognition task, and traffic classification task, simultaneously, and shows that the detection and classification performance achieved is better than the baseline methods in centralized training architecture.
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications
TLDR
Donut is proposed, an unsupervised anomaly detection algorithm based on VAE that greatly outperforms a state-of-arts supervised ensemble approach and a baseline VAE approach, and its best F-scores range from 0.75 to 0.9 for the studied KPIs from a top global Internet company.
Time-Series Anomaly Detection Service at Microsoft
TLDR
This work is the first attempt to borrow the SR model from visual saliency detection domain to time-series anomaly detection, and innovatively combine SR and CNN together to improve the performance of SR model.
...
...