Biometric authentication schemes have gained popularity due to their potential for strong security measures and user accessibility. Despite its benefits, significant concerns remain about the security and privacy of biometric data. The proposed AEGIIS (Quantum-proof Biometric Authentication: A FramEwork UtilizinG BInary Lattices and HomomorphIc Encryption for Cancelable TemplateS) secures an individual’s biometric templates through efficient arithmetic operations on binary lattices and homomorphic encryption, utilizing random noise polynomials with uniform distribution. Three benchmark data sets, ORL, CASIA-Face V5 and deep funneled LFW, were used for security and performance evaluations, resulting in Error Equal Rates of 0.000714, 0.000438, and 0.006330, respectively. The generated cancelable templates demonstrate average entropy, NPCR, and UACI values of 7.9360, 99.62 $$\%$$ , and 33.59 $$\%$$ , respectively, signifying substantially distorted templates that resist adversarial identification. The similarity score between freshly generated cancelable templates and stored CBT was evaluated against the predefined thresholds of Cosine Similarity ( $$S_{\cos }\ge 0.95$$ ), the Kolmogorov-Smirnov statistic Test ( $$S_{\text {KS}}\le 0.05$$ ) , and the Pearson Correlation Coefficient ( $$S_{\text {corr}}\ge 0.85$$ ), indicating successful authentication. The genuine and impostor distributions in the extensive data sets were used to validate the above authentication thresholds that were chosen through empirical testing. The proposed template protection method demonstrates a recognition accuracy of 99.5 $$\%$$ . The AEGIIS scheme was designed to operate on the Ring-Learning-with-Errors hardness problem, which exhibits the super polynomial complexity of $$\ {O(n \log n)}$$ and is resilient to both classical and quantum attacks and tested using indistinguishability analysis through IND-CPA analysis on ROM model, achieving post-quantum security with a key size of 256 bits.

Background and objective: The Covid-19 pandemic significantly affects the global population’s fitness and day-to-day life. The necessary action to fight against Covid is to have a fast, accurate and affordable diagnosis system. Most of the diagnostic systems available today have a low detection rate and are time consuming. Hence, there is a demand to design an affordable, accurate, and fast diagnostic system for Covid. The diagnostic system that uses the Convolutional Neural Network (CNN) does not consider the complex correlation of multimodal image data, thus misleading the diagnostic results. Graph Convolutional Network (GCN) provides a better solution for the complex representation of data, as it is modeled based on the pairwise relationship in the image features. Method: Diagnosis of Covid, Parasite, or Lung Tumor from X-ray images needs a more complex representative model. There is a demand to categorize the images grounded on highly complex features. To solve the issue mentioned earlier, this work proposes a Hypergraph- and convolutional neural network-based Fast and Accurate Diagnosis (FAT) system for Covid. The in-depth features are mined using a residual neural network from the X-ray images. The learning-based method optimizes a high-level correlation in the deep structures by constructing it as a hypergraph. Results: The proposed method is assessed based on the Covid dataset. The experimental outcomes show that the proposed system FAT provides the accuracy of 99.8%, sensitivity of 99.5%, and specificity of 99%. It outperforms all the current diagnosis systems for Covid. Conclusion: The proposed deep learning-based model is well suited for Covid diagnosis at the preliminary level. It allows diagnosing Covid by low radiation chest X-ray images with higher accuracy.