Fig. 6
From: Universal adversarial attacks on deep neural networks for medical image classification
Effect of adversarial retraining on robustness of targeted UAPs with \(p = 2\) against Inception V3 models for skin lesions, OCT, and chest X-ray image dataset. \(\zeta = 2\%\) for skin lesion and chest X-ray image datasets. \(\zeta = 6\%\) for OCT image dataset. Top panels indicate scatter plots of targeted attack success rate \(R_{s}\) (%) of UAPs versus number of iterations for adversarial retraining. Bottom panels indicate normalized confusion matrices for fine-tuned models obtained after five iterations of adversarial retraining. These confusion matrices are on adversarial test images