A Software Tool for Securing Deep Learning Against Adversarial Attacks for CAVs

Details

• Creators:
  Pisu, Pierluigi ; Comert, Gurcan ; Begashaw, Negash ; Zhao, Chunheng ; Vadnerkar, Kalpit
• Corporate Creators:
  Clemson University. Department of Automotive Engineering
• Corporate Contributors:
  Center for Connected Multimodal Mobility, Clemson University ; United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  • Autonomous vehicles
  • Computer security
  • Connected vehicles
  • Education and training methods
  • Graphical user interfaces
  • Machine learning
  • Software
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report (October 2023 - October 2024)
• Corporate Publisher:
  Center for Connected Multimodal Mobility, Clemson University
• Abstract:
  This project focuses on the technological transfer of a robust perception algorithm previously developed to mitigate adversarial attacks, transforming it into a practical software tool with an intuitive interface. The initiative builds upon the prior project, Securing Deep Learning against Adversarial Attacks for Connected and Automated Vehicles, which successfully introduced a deep ensemble network combining discriminative and generative models to counter adversarial examples. This innovative approach utilized a causal latent graph embedded in a Bayesian model to estimate adversarial perturbations, demonstrating superior accuracy and robustness when trained solely on clean data. The current project advances this work by prioritizing usability and accessibility, emphasizing the development of a graphical user interface (GUI) to facilitate the generation, training, and testing of adversary-resilient neural networks. The anticipated outcome is a tool that democratizes access to robust AI systems, enabling diverse users to enhance the security of perception systems in various applications, regardless of their expertise in deep learning.
• Format:
  PDF
• Funding:
  69A3551747117
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/83806/dot_83806_DS1.pdf
• File Type:
  [PDF - 759.99 KB]
• Collection(s):
  Artificial Intelligence Deployment Center of Excellence (AI COE) ; Autonomous Vehicles ; University Transportation Centers
• Main Document Checksum:
  urn:sha-512:b02ec150e998eaaa5eb6fb9321d6c8b794625944c0d06b2afe1c9c76bb96c38402296a9ba316bd4a173c118be734552c62c2d245563105d0aeffb65dcf1dbdb2