Energy-Efcient Transmission Range Optimization Model for WSN-Based Internet of Thing

With the explosive advancements in wireless communications and digital electronics,some tiny devices,sensors,became a part of our daily life in numerous elds.Wireless sensor networks(WSNs)is composed of tiny sensor devices.WSNs have emerged as a key technology enabling the realization of the Internet of Things(IoT).In particular,the sensor-based revolution of WSN-based IoT has led to considerable technological growth in nearly all circles of our life such as smart cities,smart homes,smart healthcare,security applications,environmental monitoring,etc.However,the limitations of energy,communication range,and computational resources are bottlenecks to the widespread applications of this technology.In order to tackle these issues,in this paper,we propose an Energy-efcient Transmission Range Optimized Model for IoT(ETROMI),which can optimize the transmission range of the sensor nodes to curb the hot-spot problem occurring in multi-hop communication.In particular,we maximize the transmission range by employing linear programming to alleviate the sensor nodes’energy consumption and considerably enhance the network longevity compared to that achievable using state-of-the-art algorithms.Through extensive simulation results,we demonstrate the superiority of the proposed model.ETROMI is expected to be extensively used for various smart city,smart home,and smart healthcare applications in which the transmission range of the sensor nodes is a key concern.

Adversarial Attacks on Featureless Deep Learning Malicious URLs Detection

Detecting malicious Uniform Resource Locators(URLs)is crucially important to prevent attackers from committing cybercrimes.Recent researches have investigated the role of machine learning(ML)models to detect malicious URLs.By using ML algorithms,rst,the features of URLs are extracted,and then different ML models are trained.The limitation of this approach is that it requires manual feature engineering and it does not consider the sequential patterns in the URL.Therefore,deep learning(DL)models are used to solve these issues since they are able to perform featureless detection.Furthermore,DL models give better accuracy and generalization to newly designed URLs;however,the results of our study show that these models,such as any other DL models,can be susceptible to adversarial attacks.In this paper,we examine the robustness of these models and demonstrate the importance of considering this susceptibility before applying such detection systems in real-world solutions.We propose and demonstrate a black-box attack based on scoring functions with greedy search for the minimum number of perturbations leading to a misclassication.The attack is examined against different types of convolutional neural networks(CNN)-based URL classiers and it causes a tangible decrease in the accuracy with more than 56%reduction in the accuracy of the best classier(among the selected classiers for this work).Moreover,adversarial training shows promising results in reducing the inuence of the attack on the robustness of the model to less than 7%on average.