تقرير
Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging
العنوان: | Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging |
---|---|
المؤلفون: | Thota, Poojitha, Veerla, Jai Prakash, Guttikonda, Partha Sai, Nasr, Mohammad S., Nilizadeh, Shirin, Luber, Jacob M. |
سنة النشر: | 2024 |
المجموعة: | Computer Science Quantitative Biology |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Quantitative Biology - Tissues and Organs |
الوصف: | In the context 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. Leveraging the Kather Colon dataset with 7,180 H&E images across nine tissue types, our investigation employs Projected Gradient Descent (PGD) adversarial perturbation attacks to induce misclassifications intentionally. The outcomes reveal a 100% success rate in manipulating PLIP's predictions, underscoring its susceptibility to adversarial perturbations. The qualitative analysis of adversarial examples delves into the interpretability challenges, shedding light on nuanced changes in predictions induced by adversarial manipulations. These findings contribute crucial insights into the interpretability, domain adaptation, and trustworthiness of Vision Language Models in medical imaging. The study emphasizes the pressing need for robust defenses to ensure the reliability of AI models. The source codes for this experiment can be found at https://github.com/jaiprakash1824/VLM_Adv_Attack. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2401.02565 |
رقم الأكسشن: | edsarx.2401.02565 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |