Explainable Anomaly Detection

Explainable Anomaly Detection is an anomaly detection framework that, as a subclass of interpretable machine learning methods, provides human-understandable justifications for detected anomalies by revealing the underlying decision logic and feature contributions that distinguish it from opaque anomaly detection models.

145

Publications

7.3K

Citations

550

Authors

228

Institutions

Publications per year

2017–2026

137

Authors

550

  1. GP
    Guansong Pang

    Singapore Management University, Singapore

    4 publications · 201 citations

    4

    h-index

  2. LR
    Lukas Ruff

    Technische Universität Berlin, Germany

    3 publications · 130 citations

    3

    h-index

  3. MA
    Mustafa Abdallah

    Indiana University – Purdue University Indianapolis, United States

    3 publications · 155 citations

    3

    h-index

  4. NM
    Nour Moustafa

    UNSW Sydney, Australia

    3 publications · 531 citations

    3

    h-index

  5. TT
    Thomas Thüm

    Technische Universität Braunschweig, Germany

    3 publications · 103 citations

    3

    h-index

1–5 of 550

Venues

  1. arXiv (Cornell University)

    Repository · 13 publications · 398 citations

    12

    h-index

  2. IEEE Access

    9 publications · 687 citations

    9

    h-index

  3. Sensors

    3 publications · 143 citations

    3

    h-index

  4. Pattern Recognition

    3 publications · 360 citations

    3

    h-index

  5. IEEE Transactions on Knowledge and Data Engineering

    TKDE · 2 publications · 164 citations

    2

    h-index

1–5