Riza Rizky Lalu M, Suyanto Suyanto
School of Computing, Telkom University, Bandung, 40257, West Java, Indonesia.
Heliyon. 2022 Dec 6;8(12):e12275. doi: 10.1016/j.heliyon.2022.e12275. eCollection 2022 Dec.
Glaucoma is an eye disease that can cause irreversible blindness to people if not treated properly. Although deep learning models have shown that they can provide good results in identifying diseases from medical imagery, they suffer from the vulnerability of adversarial attacks, making them perform poorly. Several techniques can be applied to improve defense against such attacks. One of which is adversarial training (AT) which trains a deep learning model using the input's gradient used to generate noises to the input image and Deep k-Nearest Neighbor (DkNN) that enforces prediction's conformity based on nearest neighbor voting on each layer's representation. This work tries to improve the defense against adversarial attacks by combining AT and DkNN. The evaluation performed on several adversarial attacks show that given an optimum , the combination of these two methods is able to improve most models' overall classification result on the perturbed retinal fundus image.
青光眼是一种眼部疾病，如果治疗不当会导致人们不可逆转的失明。尽管深度学习模型已表明它们在从医学图像中识别疾病方面能提供良好结果，但它们容易受到对抗攻击，导致表现不佳。有几种技术可用于改进针对此类攻击的防御。其中之一是对抗训练（AT），它使用用于向输入图像生成噪声的输入梯度来训练深度学习模型，以及深度k近邻（DkNN），它基于对每层表示的最近邻投票来强制预测的一致性。这项工作试图通过结合AT和DkNN来改进针对对抗攻击的防御。对几种对抗攻击进行的评估表明，在给定最优值的情况下，这两种方法的组合能够改善大多数模型在受干扰的视网膜眼底图像上的整体分类结果。
