Deep learning-based medical image analysis is an effective and precise method for identifying various cancer types. However, due to concerns over patient privacy, sharing diagnostic images across medical facilities is typically not permitted. Federated learning (FL) tries to construct a shared model across dispersed clients under such privacy-preserving constraints. Although there is a good chance of success, dealing with non-IID (non-independent and identical distribution) client data, which is a typical circumstance in real-world FL tasks, is still difficult for FL. We use two FL algorithms, FedAvg and FedProx, to manage client heterogeneity and non-IID data in a federated setting. A heterogeneous data split of the cancer datasets with three different forms of cancer—cervical, lung, and colon—is used to validate the efficacy of the FL. In addition, since hyperparameter optimization presents new difficulties in an FL setting, we also examine the impact of various hyperparameter values. We use Bayesian optimization to fine-tune the hyperparameters and identify the appropriate values in order to increase performance. Furthermore, we investigate the hyperparameter optimization in both local and global models of the FL environment. Through a series of experiments, we find that FedProx outperforms FedAvg in scenarios with significant levels of heterogeneity.

Biometrics combined with cryptography can be employed to solve the conceptual and factual identity frauds in digital authentication. Biometric traits are proven to provide enhanced security for detecting crimes because of its interesting features such as accuracy, stability, and uniqueness. Although diverse techniques have been raised to address this objective, limitations such as higher computational time, minimal accuracy, and maximum recognition time remain. To overcome these challenges, an enhanced iris recognition approach has been proposed based on hyperelliptic curve cryptography (HECC). The proposed study uses the 2D Gabor filter approach for perfect feature extraction in iris preprocessing. A lightweight cryptographic scheme called HECC was employed to encrypt the iris template to avoid intentional attack by the intruders. The benchmark CASIA Iris V-4 and IITD iris datasets were used in the proposed approach for experimental analysis. The result analysis witnessed that the prime objective of the research such as lesser false acceptance rate, lesser false rejection rate, maximum accuracy of 99.74%, maximum true acceptance rate of 100%, and minimal recognition time of 3 seconds has been achieved. Also, it has been identified that the proposed study outperforms other existing well-known techniques.