Diabetic Retinopathy (DR) is a result of prolonged diabetes with poor blood sugar management. It causes vision problems and blindness due to the deformation of the human retina. Recently, DR has become a crucial medical problem that affects the health and life of people. Diagnosis of DR can be done manually by ophthalmologists, but this is cumbersome and time consuming especially in the current overloaded physician’s environment. The early detection and prevention of DR, a severe complication of diabetes that can lead to blindness, require an automatic, accurate, and personalized machine learning-based method. Various deep learning algorithms, particularly convolutional neural networks (CNNs), have been investigated for detecting different stages of DR. Recently, transformers have proved their capabilities in natural language processing. Vision transformers (ViTs) are extensions of these models to capture long-range dependencies in images, which achieved better results than CNN models. However, ViT always needs huge datasets to learn properly, and this condition reduced its applicability in DR domain. Recently, a new real-world and large fundus image dataset called fine-grained annotated diabetic retinopathy (FGADR) has been released which supported the application of ViT in DR diagnosis domain. The literature has not explored FGADR to optimize ViT models. In this paper, we propose a novel ViT based deep learning pipeline for detecting the severity stages of DR based on fundus photography-based retina images. The model has been built using FGADR dataset. The model has been optimized using a new optimizer called AdamW to detect the global context of images. Because FGADR is an imbalanced dataset, we combine several techniques for handling this issue including the usage of F1-score as the optimization metric, data augmentation, class weights, label smoothing, and focal loss. Extensive experiments have been conducted to explore the role of ViT with different data balancing techniques to detect DR. In addition, the proposed model has been compared with the state-of-the-art CNN algorithms such as ResNet50, Incep-tionV3, and VGG19. The adopted model was able to capture the crucial features of retinal images to understand DR severity better. It achieved superior results compared to other CNN and baseline ViT models (i.e., 0.825, 0.825, 0.826, 0.964, 0.825, 0.825, and 0.956 for F1-score, accuracy, balanced accuracy, AUC, precision, recall, specificity, respectively). The results of the proposed ViT model were quite encouraging to be applied in real medical environment for assisting physicians to make accurate, personalized, and timely decisions.

This paper proposes a novel Convolutional Kolmogorov-Arnold Network (CKAN) model for Intrusion Detection Systems (IDS) in an IoT environment. The CKAN model is developed by replacing the Multi-Layer Perceptrons (MLPs) layers with Kolmogorov-Arnold Networks (KANs) layers inside the Convolutional Neural Networks (CNN) architecture. The KANs give high performance compared to the MLPs layers with fewer parameters. The performance of the proposed CKAN model has been evaluated against other well-known Deep Learning (DL) models like CNN, recurrent neural networks (RNN), and Autoencoder. The evaluation process has been carried out with three benchmark datasets: NSL_KDD, which is treated as a standard IDS dataset; CICIoT2023; TONIoT, which are IoT IDS datasets. The results point out the superiority of the CKAN model over other DL models for both binary and multi-classification tasks as per the accuracy, precision, recall, and F1 score. The proposed CKAN model achieved accuracies of 98.71%, 99.22%, and 99.93% for binary classification, and 99.2%, 98.84%, and 93.3% for multi-classification on the NSL_KDD, CICIoT2023, and TONIoT datasets, respectively. The CKAN model gives better performance metrics with a smaller number of parameters compared to other DL models. In this way, our findings point out that KANs are promising for being a substitute for MLPs.

Physical unclonable functions (PUF) are emerging as a promising alternative to traditional cryptographic protocols for IoT authentication. XOR Arbiter PUFs (XPUFs), a group of well-studied PUFs, are found to be secure against machine learning (ML) attacks if the XOR gate is large enough, as both the number of CRPs and the computational time required for modeling n-XPUF increases fast with respect to n, the number of component arbiter PUFs. In this paper, we present a neural network-based method that can successfully attack XPUFs with significantly fewer CRPs and shorter learning time when compared with existing ML attack methods. Specifically, the experimental study in this paper shows that our new method can break the 64-bit 9-XPUF within ten minutes of learning time for all of the tested samples and runs, with magnitudes faster than the fastest existing ML attack method, which takes over 1.5 days of parallel computing time on 16 cores.

A cloud computing environment provides a cost-effective way for the end user to store and access private data over remote storage using some Internet connection. The user has access to the data anywhere and at any time. However, the data over the cloud do not remain secure all the time. Since the data are accessible to the end user only by using the interference of a third party, it is prone to breach of authentication and integrity of the data. Moreover, cloud computing allows simultaneous users to access and retrieve their data online over different Internet connections, which leads to the exposure, leakage, and loss of a user’s sensitive data in different locations. Many algorithms and protocols have been developed to maintain the security and integrity of the data using cryptographic algorithms such as the Elliptic Curve Cryptography (ECC). This paper proposes a secure and optimized scheme for sharing data while maintaining data security and integrity over the cloud. The proposed system mainly functions by combining the ECC and the Advanced Encryption Standard (AES) method to ensure authentication and data integrity. The experimental results show that the proposed approach is efficient and yields better results when compared with existing approaches.