Visual Transformer for Resilience to Adversarial Attacks in OCT Retinal Images

Optical Coherence Tomography (OCT) is an advanced biomedical imaging technology that provides noninvasive, real-time, high-resolution images of tissues with high scattering properties. Widely employed in ophthalmology, OCT conducts diagnostic imaging of the anterior eye and retina, particularly in clinical studies evaluating its efficacy for various retinal diseases. Despite its significance, the multiple images generated by OCT pose a time-consuming challenge for ophthalmologists during the analysis process. In this paper, the pre-trained visual transformer is extended and trained with adversarial noise images. The proposed approach demonstrates the ability to effectively classify a broad spectrum of adversarial attacks while operating without prior knowledge of the attackers and without compromising classification performance. The results achieved on retinal OCT images, susceptible to adversarial attacks, exhibit a high accuracy of 98.1%.