Adversarial Anomaly Detection for Marked Spatio-Temporal Streaming Data

Spatio-temporal event data are becoming increasingly commonplace in a wide variety of applications, such as electronic transaction records, social network data, and crime incident reports. How to efficiently detect anomalies in these dynamic systems using these streaming event dataƒ This work proposes a novel anomaly detection framework for such event data combining the Long Short-Term Memory (LSTM) and marked spatio-temporal point processes. The detection procedure can be computed in an online and distributed fashion via feeding the streaming data through an LSTM and a neural network-based discriminator. This work studies the false-alarm-rate and detection delay using theory and simulation and shows that it can achieve weak signal detection by aggregating local statistics over time and networks. Finally, we demonstrate the good performance using real-world data sets.

[1]  Suleyman Serdar Kozat,et al.  Sequential Outlier Detection Based on Incremental Decision Trees , 2018, IEEE Transactions on Signal Processing.

[2]  Ian J. Goodfellow,et al.  On distinguishability criteria for estimating generative models , 2014, ICLR.

[3]  Utkarsh Upadhyay,et al.  Recurrent Marked Temporal Point Processes: Embedding Event History to Vector , 2016, KDD.

[4]  Jason Eisner,et al.  The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process , 2016, NIPS.

[5]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[6]  See-Kiong Ng,et al.  Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series , 2018, ArXiv.

[7]  Emanuele Ghelfi,et al.  A Survey on GANs for Anomaly Detection , 2019, ArXiv.

[8]  Alfred O. Hero,et al.  Anomaly Detection in Partially Observed Traffic Networks , 2018, IEEE Transactions on Signal Processing.

[9]  Marius Kloft,et al.  Image Anomaly Detection with Generative Adversarial Networks , 2018, ECML/PKDD.

[10]  Xin Liu,et al.  Improving Maximum Likelihood Estimation of Temporal Point Process via Discriminative and Adversarial Learning , 2018, IJCAI.

[11]  Ulrike Goldschmidt,et al.  An Introduction To The Theory Of Point Processes , 2016 .

[12]  Panos P. Markopoulos,et al.  Adaptive L1-Norm Principal-Component Analysis With Online Outlier Rejection , 2018, IEEE Journal of Selected Topics in Signal Processing.

[13]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[14]  Georg Langs,et al.  f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks , 2019, Medical Image Anal..

[15]  Bin Tong,et al.  Active Generative Adversarial Network for Image Classification , 2019, AAAI.

[16]  Chris Dyer,et al.  Notes on Noise Contrastive Estimation and Negative Sampling , 2014, ArXiv.