Universal Adversarial Framework to Improve Adversarial Robustness for Diabetic Retinopathy Detection
This work addresses the critical need for robust AI in healthcare by improving adversarial robustness for diabetic retinopathy detection, though it is incremental as it applies existing UAP methods to a new medical domain.
The paper tackles the vulnerability of deep learning systems for diabetic retinopathy detection to adversarial attacks by using universal adversarial perturbations (UAPs) to both attack and defend models, resulting in an average performance boost of 3.41 Cohen-kappa against unseen attacks with minimal degradation on normal data.
Diabetic Retinopathy (DR) is a prevalent illness associated with Diabetes which, if left untreated, can result in irreversible blindness. Deep Learning based systems are gradually being introduced as automated support for clinical diagnosis. Since healthcare has always been an extremely important domain demanding error-free performance, any adversaries could pose a big threat to the applicability of such systems. In this work, we use Universal Adversarial Perturbations (UAPs) to quantify the vulnerability of Medical Deep Neural Networks (DNNs) for detecting DR. To the best of our knowledge, this is the very first attempt that works on attacking complete fine-grained classification of DR images using various UAPs. Also, as a part of this work, we use UAPs to fine-tune the trained models to defend against adversarial samples. We experiment on several models and observe that the performance of such models towards unseen adversarial attacks gets boosted on average by $3.41$ Cohen-kappa value and maximum by $31.92$ Cohen-kappa value. The performance degradation on normal data upon ensembling the fine-tuned models was found to be statistically insignificant using t-test, highlighting the benefits of UAP-based adversarial fine-tuning.