Inherent broadcast characteristics can raise privacy risks of wireless networks. The specifics of antenna ports, antenna types, orientation, and beamforming configurations of a transmitter can be susceptible to manipu...
详细信息
Inherent broadcast characteristics can raise privacy risks of wireless networks. The specifics of antenna ports, antenna types, orientation, and beamforming configurations of a transmitter can be susceptible to manipulation by any device within range when the signal is transmitted wirelessly. Personal and location information of users connected to the transmitter can be intercepted and exploited by malicious actors to track user movements and profile behaviors or launch targeted attacks, thus compromising user privacy and security. In this paper, we propose a novel precoding perturbation approach for privacy preservation in wireless communications. Our approach perturbs the precoding matrix of the transmitter using a Riemannian manifold (RM) structure that adaptively adjusts the magnitude and direction of perturbation based on the geometric properties of the manifold. The approach ensures robust privacy protection while minimizing the distortion of the transmitted signals, thus balancing privacy preservation and data utility. Privacy can be preserved without relying on additional cryptographic mechanisms, resulting in the computational and communication overhead reduction. Our approach operates directly on the transmission of signals, making them inherently secure against eavesdropping and interception. Simulation results underscore the superiority of the approach, showing a 17.21% improvement in privacy preservation while effectively maintaining data utility.
作者:
Du, SichunZhu, HaodiZhang, YangHong, QinghuiHunan University
College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University
Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China
Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN)...
详细信息
Microcomputers and medical devices with signal transceivers that operate on a specific radio display constitute the backbone of wireless sensor networks (WS Ns) that monitor environmental conditions (temperature, pres...
详细信息
The objective of Advanced Persistent Threat (APT) attacks is to exploit Cyber-Physical Systems (CPSs) in combination with the Industrial Internet of Things (I-IoT) by using fast attack methods. Machine learning (ML) t...
详细信息
The performance of SDN-based LEO satellite networks significantly depends on the control domain division approaches. The dynamical topology in LEO networks results in the time-varying delay for network management. The...
详细信息
Communication efficiency is one of the key bottlenecks in Federated Learning (FL). Compression techniques, such as sparsification and quantization, are used to reduce communication overhead. However, joint designs of ...
详细信息
Cyber Threat Intelligence (CTI) involves collecting and analyzing cyber security data using advanced algorithms and rigorous techniques to identify and address potential threats, harmful incidents, and existing vulner...
详细信息
The evolving digital environment requires sophisticated decision systems to protect important information assets from the growing complexity and variety of cyber threats. This review paper examines the impact of machi...
详细信息
ISBN:
(纸本)9789819601462
The evolving digital environment requires sophisticated decision systems to protect important information assets from the growing complexity and variety of cyber threats. This review paper examines the impact of machine learning (ML) on cybersecurity decision systems, with a specific focus on analyzing ML and deep learning (DL) methods. The study employs the UNSW-NB15 dataset, which is a widely used benchmark dataset in the field of network security. The paper starts with an overview of the present cybersecurity environment, emphasizing the difficulties presented by advanced and changing cyber threats. It highlights the importance of adaptive and intelligent decision systems that can efficiently identify and reduce cyberattacks as they occur. A significant part of the paper focuses on a thorough analysis of different machine learning and deep learning techniques used in cybersecurity. The review discusses conventional machine learning algorithms like decision trees, support vector machines, and ensemble methods, along with sophisticated deep learning architectures such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Each approach is thoroughly assessed for its strengths and limitations based on factors like accuracy, interpretability, and scalability. The performance of various ML and DL models is evaluated using the UNSW-NB15 dataset as a benchmark. The dataset covers various cyberattack scenarios, enabling a thorough assessment of algorithms’ ability to detect anomalies and classify malicious activities. The paper explores the incorporation of machine learning (ML) and deep learning (DL) into decision support systems, highlighting the significance of explainability and interpretability in the realm of cybersecurity. The conversation covers the difficulties of implementing machine learning (ML) and deep learning (DL) models in practical situations, such as concerns about data privacy, adversarial attacks, and model resilience. This rev
To enhance the handover performance in fifth generation (5G) cellular systems, conditional handover (CHO) has been evolved as a promising solution. Unlike A3 based handover where handover execution is certain after re...
详细信息
In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic agg...
详细信息
In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic aggregation functions include SELECTION(select the k-th largest or smallest element),DISTINCT(query the count of distinct elements), MODE(query the most frequent element). We design three basic techniques — Pre-order Network Partition, Pairwise-independent Random Walk, and Random Permutation Delivery, and devise the algorithms based on the techniques. The round complexity of the distributed SELECTION is Θ(log N) which meets the lower bound where N is the number of nodes and each node holds a numeric element. The round complexity of the distributed DISTINCT and MODE algorithms are O(log3N/log log N) and O(log2N log log N) respectively. All of our results break the lower bounds obtained on general graphs and our distributed algorithms are all based on the CON GE S T model, which restricts each node to send only O(log N) bits on each edge in one round under synchronous communications.
暂无评论