arXiv Machine Learning August 6, 2026 By Simon Kl\"uttermann, J\'er\^ome Rutinowski, Frederik Polachowski, Alice Kirchheim

Why Ranking Anomaly Detection Algorithms Isn't as Reliable as You May Think

Read the original on arXiv Machine Learning →

arXiv:2608. 04613v1 Announce Type: new Abstract: Anomaly detection is a safety-critical machine learning problem with applications ranging from fraud detection to network intrusion prevention and industrial monitoring.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 19

We Need to Rethink Benchmarking in Anomaly Detection

arXiv:2507. 15584v2 Announce Type: replace Abstract: Despite the continuous proposal of new anomaly detection algorithms and extensive benchmarking efforts, progress seems to stagnate, with only minor performance differences between established baselines and new algorithms.

By Philipp R\"ochner, Simon Kl\"uttermann, Kevin Kammler, Franz Rothlauf, Emmanuel M\"uller, Daniel Schl\"or

benchmarks

arXiv AI

Jul 22

Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios

arXiv:2607. 18289v1 Announce Type: cross Abstract: Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes.

By Kamil Faber, Mateusz Smendowski, Roberto Corizzo

benchmarks

arXiv Machine Learning

Aug 12

DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches

arXiv:2509. 05663v4 Announce Type: replace Abstract: Truly unsupervised approaches for time series anomaly detection are rare in the literature.

By Lucas Correia, Jan-Christoph Goos, Thomas B\"ack, Anna V. Kononova

arXiv Machine Learning

Sep 24

Anomaly-Free Self-Optimization via AUC Bounds

arXiv:2609.27362v1 Announce Type: new Abstract: Anomalies are rare, and anomalous data are often unavailable during development, making it difficult to determine which anomaly detection models and co...

By Kevin Wilkinghoff, Zheng-Hua Tan

rag

arXiv Machine Learning

Sep 23

Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?

The paper investigates whether the performance of anomaly detection systems can be predicted without labeled anomalies. For kNN-based detectors, it derives a lower bound on AUC that links detection performance to the separation and variance of inlier and outlier scores, and uses this to analyze how density variation, intrinsic dimensionality, and domain mismatch affect score variability. The authors introduce pseudo‑anomaly probes that provide a reference for estimating relative score separation, and demonstrate through experiments on DCASE benchmarks that these probes enable anomaly‑free model selection to outperform conventional development‑set selection, especially under domain shift.

By Kevin Wilkinghoff, Zheng-Hua Tan

rag benchmarks

arXiv AI

Aug 25

Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings

arXiv:2507.12295v2 Announce Type: replace-cross Abstract: Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation id...

By Feng Xiao, Jicong Fan

llms rag nlp benchmarks

One email a morning, machine-written

Related stories

We Need to Rethink Benchmarking in Anomaly Detection

Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios

DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches

Anomaly-Free Self-Optimization via AUC Bounds

Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?

Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddings