GitHub / jaiprakash1824 / VLM_Adv_Attack

In the dynamic landscape of medical artificial intelligence, this study explores the vulnerabilities of the Pathology Language-Image Pretraining (PLIP) model, a Vision Language Foundation model, under targeted attacks like PGD adversarial attack.

JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jaiprakash1824%2FVLM_Adv_Attack

Topics: adversarial-attacks, attention-mechanism, attention-visualization, clip, contrastive-learning, histopathology-image-classfication, histopathology-images, pathology, pathology-image, pgd-adversarial-attacks, plip-model, pytorch, trustworthiness, trustworthy-ai, trustworthy-machine-learning, vision-language-model, vision-transformer, vulnerability-detection

Files

No dependencies found