Preserving the performance of a trained model while removing unique characteristics marked training data points is challenging. Recent research usually suggests retraining from scratch with remaining or refining by reverting optimization on points. Unfortunately, aside their computational inefficiency, those approaches inevitably hurt resulting model's generalization ability since they remove n...

Due to advancements in malware competencies, cyber-attacks have been broadly observed the digital world. Cyber-attacks can hit an organization hard by causing several damages such as data breach, financial loss, and reputation loss. Some of most prominent examples ransomware attacks history are WannaCry Petya, which impacted companies’ finances throughout globe. Both Petya caused operational pr...

Retinal vessel segmentation is a fundamental step in screening, diagnosis, and treatment of various cardiovascular ophthalmic diseases. Robustness one the most critical requirements for practical utilization, since test images may be captured using different fundus cameras, or affected by pathological changes. We investigate this problem from data augmentation perspective, with merits no additi...

In spite of the significant advancement in face recognition expertise, accurately recognizing same individual across different ages still remains an open research question. Face aging causes intra-subject variations (such as geometric changes during childhood adolescence, wrinkles and saggy skin old age) which negatively affects accuracy systems. Over years, researchers have devised techniques ...

In this paper we perform an in depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, propose methods to deal with channel variability, different compressions, bandwidths and unseen spoofing attacks. These challenges, have all been shown significantly degrade the performance based systems anti systems. Our results are on ASVspoof 2021 challen...