ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hermary, Romain, Hicsonmez, Samet, Pineau, Dan, Shabayek, Abd El Rahman, Aouada, Djamila
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914527058067456
author Hermary, Romain
Hicsonmez, Samet
Pineau, Dan
Shabayek, Abd El Rahman
Aouada, Djamila
author_facet Hermary, Romain
Hicsonmez, Samet
Pineau, Dan
Shabayek, Abd El Rahman
Aouada, Djamila
contents Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.
format Preprint
id arxiv_https___arxiv_org_abs_2604_13924
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection
Hermary, Romain
Hicsonmez, Samet
Pineau, Dan
Shabayek, Abd El Rahman
Aouada, Djamila
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.
title ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.13924