• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Anderes
  4. Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
 
  • Details
  • Full
Options
2022
Paper (Preprint, Research Paper, Review Paper, White Paper, etc.)
Title

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection

Title Supplement
Published on arXiv
Abstract
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to the human eye. In recent years, various approaches have been proposed to defend CNNs against such attacks, for example by model hardening or by adding explicit defence mechanisms. Thereby, a small "detector" is included in the network and trained on the binary classification task of distinguishing genuine data from data containing adversarial perturbations. In this work, we propose a simple and light-weight detector, which leverages recent findings on the relation between networks' local intrinsic dimensionality (LID) and adversarial attacks. Based on a re-interpretation of the LID measure and several simple adaptations, we surpass the state-of-the-art on adversarial detection by a significant margin and reach almost perfect results in terms of F1-score for several networks and datasets. Sources available at: https://github.com/adverML/multiLID
Author(s)
Lorenz, Peter
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Keuper, Margret
sl-0
Keuper, Janis  
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Conference
International Conference on Computer Vision Theory and Applications 2023  
Open Access
File(s)
Download (583.27 KB)
Rights
CC BY-NC-ND 4.0: Creative Commons Attribution-NonCommercial-NoDerivatives
DOI
10.48550/arXiv.2212.06776
10.24406/publica-846
Language
English
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM  
Keyword(s)
  • Adversarial examples

  • detection

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