Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM

2018/03/06 by Chase Roberts, Roberts, Chase, Manish Nair +1
Computer Science · #Algorithms and Data Compression #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.1803.02395

openalex publication_date 2018/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a simple mathematical definition and new neural architecture for finding anomalies within discrete sequence datasets. Our model comprises of a modified LSTM autoencoder and an array of One-Class SVMs. The LSTM takes in elements from a sequence and creates context vectors that are used to predict the probability distribution of the following element. These context vectors are then used to train an array of One-Class SVMs. These SVMs are used to determine an outlier boundary in context space.We show that our method is consistently more stable and also outperforms standard LSTM and sliding window anomaly detection systems on two generated datasets.

Citations

• Adam: A Method for Stochastic Optimization

Related

• Unsupervised Online Anomaly Detection On Irregularly Sampled Or Missing Valued Time-Series Data Using LSTM Networks
• Improved AutoEncoder with LSTM module and KL divergence
• Fine-grained Anomaly Detection in Sequential Data via Counterfactual Explanations
• Anomaly detection using prediction error with Spatio-Temporal Convolutional LSTM
• Anomaly Detection using One-Class Neural Networks