The Internet of Things has transformed daily life by connecting devices that collect and share data, significantly impacting fields like healthcare. However, managing the massive data generated by these devices poses challenges. Context-aware recommendation systems can address this by providing tailored suggestions based on the user’s context and their environment. This paper focuses on applying such systems in healthcare to combat the spread of contagious diseases. Building on lessons from Covid-19 and recent outbreaks like Mpox and Marburg, we aim to design and implement a context-aware recommendation system that helps users identify the most vulnerable areas for epidemic spread, allowing them to avoid these locations.
Digital signatures are crucial for blockchain security, ensuring transaction authenticity, integrity, and nonrepudiation. This reliance on secure digital signatures also extends to emerging blockchain applications like in the Internet of Vehicles (IoV) and the Internet of Devices (IoD). However, the emergence of Post-Quantum Cryptography (PQC) poses a potential threat to blockchain performance by significantly increasing the size of digital signatures and public keys. This paper examines the number of signatures per block in the Bitcoin network using a real-world data-driven analysis. We propose an efficient signature counting algorithm that processes transaction data and accounts for all acceptable digital signature formats. To evaluate the methodology and the quality of the data, we apply the Shapiro-Wilk test for normality and use the Coefficient of Variation (CV) to assess data distribution and variability. This research advances blockchain analytics by offering a systematic approach to quantifying digital signatures.
In recent years, Generative Adversarial Networks (GANs) have emerged as powerful tools for improving signal processing in advanced communication systems, particularly in the context of 5G networks. In this paper, we present a novel approach for distinguishing signal from noise in 5G Multiple Input Multiple Output (MIMO) systems using GANs. Our method leverages the generative capabilities of GANs to produce realistic noise signals and the discriminative power of GANs to accurately identify real signals amidst noise. By training the GAN on a combination of real-world noisy signals and pure noise, our model achieves robust signal detection and classification. We evaluate our approach using synthetic data, demonstrating significant improvements over other techniques such as the autoencoders. Our results highlight the potential of GANs in enhancing the reliability and performance of 5 G MIMO communications.
Every day, on average, eight cybercrimes targeting IoT networks occur, leading to a cumulative loss of $10 million. The main reason for these attacks is the ability of unauthorized devices to gain access to IoT networks by replicating the hardware and software configurations of authorized devices. To tackle this pressing issue, cryptographic keys are used to authenticate devices in IoT networks. Given the requirements of this process, authentication is performed once at the beginning. However, this makes devices susceptible to cyber-attacks like spoofing, Sybil attacks, distributed denial-of-service (DDoS), and Advanced Persistent Threats (APT). To address this, we propose a novel Continuous Device-to -Device Authentication (CD2A) framework based on two components: 1) Identity Establishment and 2) Continuous Authentication. In the Identity Establishment phase, we use manufacturing imperfections to model unique device behaviours. A novel device fingerprint algorithm is proposed that leverages impurities of built-in components of the device, like crystal oscillators, and is measured in a graphical processing unit (GPU) by isolating each core at a time in the central processing unit (CPU). In the Continuous Authentication phase, we implement a dynamic timeline to establish device identity at regular intervals. Each device is continuously authenticated by using machine learning techniques. To protect devices from cyber-attacks like spoofing, Sybil attacks, DDoS, and APT, we track device legitimacy by calculating the Device Authentication Score (DAS) and the Device Risk Factor (DRF) in view of varying security risks. We evaluate the CD(2)A framework on an IoT system with 11 devices. The CD(2)A framework achieves an average authentication accuracy of 99.96% and 99.85% when used in tandem with CatBoost and XGBoost machine learning algorithms, respectively.
In this work-in-progress, we introduce the concept of private embeddings for biometric recognition. We explain how a portion of the neural network responsible for embedding images can be personalized and kept separate for use during the comparison phase. We propose a biometric system that incorporates these private embeddings while ensuring the confidentiality of the underlying biometric data.
