Jeongjin Shin
blog / publications / projects / work
Publications

Peer-reviewed conference papers, preprints, and research on Trustworthy AI, backdoor vulnerabilities, and machine learning security.

  • Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models arXiv (2024)
    Investigates deferred backdoor functionality attacks that survive machine unlearning and parameter scrubbing in deep neural networks.
  • Mask-based Invisible Backdoor Attacks on Object Detection IEEE ICIP (2024)
    Proposes imperceptible mask-based backdoor insertion techniques tailored for object detection architectures.
© 2026 | Jeongjin Shin