With the booming integration of IoT technology in our daily life applications such as smart industrial, smart city, smart home, smart grid, and healthcare, it is essential to ensure the security and privacy challenges of these systems. Furthermore, time-critical IoT applications in healthcare require access from external parties (users) to their real-time private information via wireless communication devices. Therefore, challenges such as user authentication must be addressed in IoT wireless sensor networks (WSNs). In this paper, we propose a secure and lightweight three-factor (3FA) user authentication protocol based on feature extraction of user biometrics for future IoT WSN applications. The proposed protocol is based on the hash and XOR operations, including (i) a 3-factor authentication (i.e., smart device, biometrics, and user password); (ii) shared session key; (iii) mutual authentication; and (iv) key freshness. We demonstrate the proposed protocol’s security using the widely accepted Burrows–Abadi–Needham (BAN) logic, Automated Validation of Internet Security Protocols and Applications (AVISPA) simulation tool, and the informal security analysis that demonstrates its other features. In addition, our simulations prove that the proposed protocol is superior to the existing related authentication protocols, in terms of security and functionality features, along with communication and computation overheads. Moreover, the proposed protocol can be utilized efficiently in most of IoT’s WSN applications, such as wireless healthcare sensor networks.

Deep neural network-based computer vision applications have exploded and are widely used in intelligent services for IoT devices. Due to the computationally intensive nature of DNNs, the deployment and execution of intelligent applications in smart scenarios face the challenge of limited device resources. Existing job scheduling strategies are single-focused and have limited support for large-scale end-device scenarios. In this paper, we present ADDP, an adaptive distributed DNN partition method that supports video analysis on large-scale smart cameras. ADDP applies to the commonly used DNN models for computer vision and contains a feature-map layer partition module (FLP) supporting edge-to-end collaborative model partition and a feature-map size partition (FSP) module supporting multidevice parallel inference. Based on the inference delay minimization objective, FLP and FSP achieve a tradeoff between the arithmetic and communication resources of different devices. We validate ADDP on heterogeneous devices and show that both the FLP module and the FSP module outperform existing approaches and reduce single-frame response latency by 10–25% compared to the pure on-device processing.