Skip to main content
Search

# BAPLe++

1 related articles

Subscribe to updates
  1. arXiv

    Backdoors in medical foundation models survive a model swap: BAPLe++ repairs the prompt and cuts attack success more consistently across four models and six datasets

    Medical foundation models are often adapted with prompt learning, which trains a few prompt tokens while the backbone stays frozen; BAPLe++ asks whether a backdoor implanted during that adaptation travels with the prompt to a different medical foundation model, and proposes DePLe, which treats the infected prompt as a fixed anchor and learns a new prompt on a small clean set. Across MedCLIP, BioMedCLIP, PLIP and QuiltNet and six chest X-ray and histopathology datasets, backdoors do transfer across models, but asymmetrically and in a dataset-dependent way; compared with four training-free input transformations, DePLe reduces backdoor accuracy more consistently while preserving, and in some settings improving, clean accuracy.

You’re all caught up