• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Scopus
  4. R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
 
  • Details
  • Full
Options
2023
Conference Paper
Title

R2-AD2: Detecting Anomalies by Analysing the Raw Gradient

Abstract
Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss. Samples unlike the ones seen during training cause a different gradient distribution. Based on this intuition, we design a novel semi-supervised anomaly detection method called R2-AD2. By analysing the temporal distribution of the gradient over multiple training steps, we reliably detect point anomalies in strict semi-supervised settings. Instead of domain dependent features, we input the raw gradient caused by the sample under test to an end-to-end recurrent neural network architecture. R2-AD2 works in a purely data-driven way, thus is readily applicable in a variety of important use cases of anomaly detection.
Author(s)
Schulze, Jan-Philipp  
Fraunhofer-Institut für Angewandte und Integrierte Sicherheit AISEC  
Sperl, Philip  
Fraunhofer-Institut für Angewandte und Integrierte Sicherheit AISEC  
Răduțoiu, Ana Teodora
Sagebiel, Carla
Böttinger, Konstantin  
Fraunhofer-Institut für Angewandte und Integrierte Sicherheit AISEC  
Mainwork
Machine Learning and Knowledge Discovery in Databases. European Conference, ECML PKDD 2022. Proceedings. Pt.I  
Conference
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2022  
DOI
10.1007/978-3-031-26387-3_13
Language
English
Fraunhofer-Institut für Angewandte und Integrierte Sicherheit AISEC  
Keyword(s)
  • Anomaly detection

  • Data mining

  • Deep learning

  • IT security

  • Semi-supervised learning

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024