machine learning, computer vision

It is mandatory to evaluate the strength of CNN models used in medical tasks against adversarial attacks especially in healthcare; that is to say, the security of such models is becoming extremely relevant to the diagnosis as this latter will guide high-stakes decision-making. , In order to defend against malicious attacks we went to Implementation data poisoning and feature provenance described in this notebook ' ---------- ' to our Unet mobile net Segmentation models ' the notebook will be shared later'