• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
 
  • Details
  • Full
Options
2023
Conference Paper
Title

Are Transformers More Robust? Towards Exact Robustness Verification for Transformers

Abstract
As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving. In this paper, we study the robustness problem of Transformers, a key characteristic as low robustness may cause safety concerns. Specifically, we focus on Sparsemax-based Transformers and reduce the finding of their maximum robustness to a Mixed Integer Quadratically Constrained Programming (MIQCP) problem. We also design two pre-processing heuristics that can be embedded in the MIQCP encoding and substantially accelerate its solving. We then conduct experiments using the application of Land Departure Warning to compare the robustness of Sparsemax-based Transformers against that of the more conventional Multi-Layer-Perceptron (MLP) NNs. To our surprise, Transformers are not necessarily more robust, leading to profound considerations in selecting appropriate NN architectures for safety-critical domain applications.
Author(s)
Liao, Brian Hsuan-Cheng
Denso Automotive
Cheng, Chih-Hong  
Fraunhofer-Institut für Kognitive Systeme IKS  
Esen, Hasan
Denso Automotive
Knoll, Alois
Technische Universität München  
Mainwork
Computer Safety, Reliability, and Security. 42nd International Conference, SAFECOMP 2023. Proceedings  
Project(s)
FOUNDATIONS FOR CONTINUOUS ENGINEERING OF TRUSTWORTHY AUTONOMY  
Funder
European Commission  
Conference
International Conference on Computer Safety, Reliability and Security 2023  
DOI
10.1007/978-3-031-40923-3_8
Language
English
Fraunhofer-Institut für Kognitive Systeme IKS  
Fraunhofer Group
Fraunhofer-Verbund IUK-Technologie  
Keyword(s)
  • neural networks

  • NN

  • transformer

  • robustness

  • safety

  • Mixed Integer Quadratically Constrained Programming

  • MIQCP

  • Multi-Layer-Perceptron

  • MLP

  • safety-critical

  • neural networks verification

  • lane departure warning

  • autonomous driving

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