Connected autonomous vehicles (CAVs) rely on object detection models to ensure safe and efficient navigation. Traditional centralized training approaches pose challenges related to data privacy, scalability, and communication overhead. In this study, we integrate Federated Learning (FL) with YOLO models, including YOLOv5, YOLOv8, and YOLOv11, for object detection in CAVs, utilizing the Flower framework to enable decentralized training while preserving data privacy. We design a virtual client setup that replicates a realistic scenario and apply FedAvg and FedProx aggregation strategies on the KITTI and BDD100K datasets. Our experimental results demonstrate that FL-based training outperforms traditional centralized learning, with YOLOv8 achieving a mean average precision (mAP) of 87.9% in KITTI and 61.5% in BDD100K, outperforming the baseline. Our study highlights the feasibility and effectiveness of deploying FL-based object detection models in CAVs, by conducting a comprehensive evaluation of using the Flower federated learning framework and addressing privacy concerns through decentralized training.

Federated learning (FL) enables collaborative model training across edge devices without centralizing raw data, but existing frameworks remain ill-equipped to support data privacy regulations mandated by GDPR, HIPAA, and CCPA. Once user data has influenced training, its verifiable removal becomes prohibitively expensive, particularly in non-IID and resource-constrained edge environments. This paper introduces a modular and scalable federated unlearning framework that unifies three complementary strategies: gradient subtraction, knowledge distillation, and checkpoint rollback, within an adaptive decision layer. A resource-aware checkpoint manager reduces storage costs through compression and pruning, while a privacy and trust layer integrates zero-knowledge proofs, differential privacy, and Merkle-based audit logs to provide verifiable guarantees of deletion. A non-IID-aware aggregator further preserves fairness across heterogeneous clients. Unlike prior approaches, our proposed framework systematically integrates rollback efficiency with formal privacy protections and auditability, offering a practical path toward trustworthy and regulation-compliant unlearning in domains such as healthcare, transportation, and smart agriculture.

In consortium applications, multiple organizations collaborate on a common goal. The complex consortium structure makes it a significant challenge to achieve the goals of both secure collaboration and preserving each organization’s data confidentiality. Existing security architectures are insufficient to tackle the above challenge. This article proposes ConsortiumSec, a blockchain-based two-layer distributed security architecture. ConsortiumSec leverages disruptive blockchain technologies to systematically address the security issues in consortium applications, including consortium membership management, access control, secure storage, governance policy management, and privacy preservation. The Hyperledger Fabric-based prototype implementation demonstrates the proposed architecture not only integrates the organization’s existing security mechanisms but also ensures a secure collaborative environment. The case study based on a real-world consortium application demonstrates the effectiveness of ConsortiumSec.

In the current big data landscape, where data forms the cornerstone of myriad applications, it is crucial to establish the reliability and credibility of application outcomes through the prism of high-quality data. Nonetheless, data quality has been facing significant evaluation challenges due to the exponential increase in data volume and diversity. This paper introduces a novel big data quality scoring (BDQS) model, which is particularly designed for assessing the quality of large-scale datasets within the Hadoop MapReduce ecosystem. Unlike other models that either focus on smaller datasets or rely on sampling techniques, BDQS excels in providing comprehensive data quality assessment for substantial data sources. Specifically, BDQS identifies accuracy, completeness, consistency, timeliness, and correlation as critical dimensions of data quality, scores each dimension on a scale of 0 to 100, and derives an aggregate data quality score through binomial testing and standard normalization of these scores. This research advances a potent model for big data quality assessment and offers valuable insights for enhancing the reliability and applicability of large-scale datasets across various sectors.

With the development of the Internet of Everything (IoE), huge amount of data is being generated at network edge and needs to be processed in real time, such as edge video analytics applications. However, limited computing resources and energy on edge devices make it challenging to efficiently perform the intensive computing tasks. Existing solutions of offloading tasks to edge servers depend on the availability of edge servers, and they are difficult to satisfy massive computation needs. Instead, this article proposes a novel offloading framework named EdgeBrain, which offloads computational tasks from one edge device (Producer of Computation, i.e., PCO) to other edge devices (Consumers of Computation, i.e., CCOs). We formulate this offloading problem as a multi-round non-cooperative Stackelberg game, prove the existence of unique Nash Equilibrium (NE) and Stackelberg Equilibrium (SE) in the game, and design the gradient search algorithm to calculate the optimal offloading decision. The performance evaluation based on a prototype implementation of EdgeBrain in the context of a video analytics application, face detection and recognition, shows that EdgeBrain outperforms several comparable techniques in terms of execution time, frame rate, transfer data volume, and power consumption.

Millions of Wi-Fi cameras have been deployed in businesses and households in the last decade. Most of them are used to provide security surveillance services. It raises new security concerns because these cameras could become the target of various attacks. Among them, Evil Twin, Deauthentication, and Disassociation attacks are well-known, easy-to-launch, and dangerous ones. However, there is a lack of deep understanding and awareness of these attacks, as well as efficient mitigation mechanisms. In this paper, we design a set of experiments to demonstrate how easily and effectively these attacks can be launched from simple computing platforms like Raspberry Pi using publicly available, open-source, and easy-configurable tools toward a set of carefully selected, popular, and highly reputed Wi-Fi cameras. Based on our testing, we report our interesting observations and discuss the mitigation approaches. We believe these attacks are beyond cameras and we hope our work can bring serious attention to the security of Wi-Fi equipped devices.

Welcome to the ICCCN 2023 Workshops! As an integral part of the main conference, the ICCCN workshop program provides international forums for scientists and engineers from both academia and industry to exchange and share their experiences, research results, and new ideas on hot and emerging topics on computer communications and networks. This year we enjoyed the great privilege to have worked with researchers across the world in organizing three workshops covering a variety of important, exciting and timely topics in the area of computer communications and networks. We received a good number of high-quality papers. These workshops are:

Bandwidth-intensive applications transmit large-scale video data in the network. It causes backhaul bottlenecks and affects user experience. Deploying edge cache on an access point (AP) is a popular method to bring content files closer to end-users, but it faces significant challenges, especially in efficiently predicting and satisfying different users’ future content requests with limited cache capacity. In this article, we propose an intelligent gateway assisted edge cache deployment strategy (GACD), which jointly considers traffic usage patterns in multiple APs and the impact of new content on the cache performance. In GACD, The cache content placement problem is formulated as a many-to-one bidirectional matching problem with a dynamic quota allocation, aiming to improve cache resource utilization and minimize the average delivery latency. To address this problem, we design a heterogeneous information networks based prediction algorithm to predict end-users’ potential preference of new content files. Then, we adapt the seasonal autoregressive integrated moving average model for traffic usage prediction, and propose a many-to-one matching algorithm to achieve dynamic matching quota adjustment and efficient cache content placement. We conduct extensive real-world trace-based experiments to validate the performance of GACD. Compared with six alternative cache strategies, GACD improves the hit rate by 23.9% on average, reduces the average content delivery delay by 19.02%, and increases the accuracy by 31.02% on average.

Cloud storage services improve the efficiency and popularity of data sharing. These services allow groups of participants to jointly maintain the shared data. As important security properties of cloud data sharing, the integrity and the reliability of the shared data have been studied recently. However, the existing research cannot sufficiently solve the issue of participant identity anonymity in the scenario of data modification. In this paper, we propose a novel approach to achieve fully anonymous integrity checking and reliability authentication for cloud data sharing. We design a predicate for the shared data, and construct the Lagrange interpolation polynomials for all participants to compute the secret keys based on the designed predicate. When modifying the shared data, the participants compute the authenticators of the modified data using the secret key associated with the designed predicate instead of their identities. In this way, the integrity checking and reliability authentication of the shared data modified by different participants can be performed while the identities of the corresponding participants remain fully anonymous. In addition, the traceability and revocation of participant identity are considered. The performance analysis demonstrates the efficiency of the proposed approach, and the security analysis shows that the proposed approach satisfies the desired properties.

Given the eruption of Internet of Things (IoT) systems, it has become critical for connected devices to have persistent security. Password-based security measures provide an interface for users to effectively secure their personal data. Nonetheless, passwords are often stolen by cyber criminals due to inferior user security awareness. To address these issues, in this paper, we develop a renewal-reward process-based password protection$(R^{2}P^{3})$scheme to prevent unauthorized users from breaching IoT devices even after they obtain user passwords. Specifically,$R^{2}P^{3}$utilizes the renewal-reward process to accu-mulate a tendency to trust$(T^{3})$score for any$\mathbf{IoT}$device password attempt on the basis of keystroke dynamics (i.e., dwell time and flight time) and assures device authentication by comparing user attempt$T^{3}$scores to a predefined threshold. We have validated the security efficacy of$R^{2}P^{3}$. Our experimental results demonstrate that$R^{2}F^{3}$achieves superior security performance in terms of unauthorized user blocking ratio.

Given the explosion of e-services, it has become critical for recommender systems (RSs) to have expected suggestions. Traditional machine learning-based recommending models provide an interface for platforms to find the most relevant items for users. Nonetheless, those models are often trained with user data from a single domain at centralized cloud, which hinders the performance of RSs, causes significant data transmission overhead, and may harm data privacy. To address these issues, in this poster, we propose an ensemble federated edge learning scheme (eFEEL) on the basis of a semi-distributed architecture design. eFEEL aims to efficiently and effectively improve RSs without breaching user data privacy.

Data quality is essential to pricing big data and deciding its trading profit in digital market. Traditional machine learning-based data quality assessment methods support the valuation of data assets. Nonetheless, these methods require data to be sent over and assessed at centralized cloud, which incurs unprecedented data transmission cost and may jeopardize data privacy. To address these issues, in this poster, we propose a privacy-preserving big data quality assessment scheme (p2QA) on the basis of blockchain and federated edge learning (FEEL). p2QA aims to notably reduce data transmission cost, accurately measure big data quality, and effectively prevent malicious parties from violating data privacy.

Cloud computing and edge computing models are popularly applied in emerging applications, such as smart homes, smart parks, and connected autonomous vehicles for large-scale live video analytics. Cloud computing-based models transfer all data to the cloud for video analytics, which burdens network bandwidth and increases the data transmission overhead. Edge computing mode enables video data to be processed at the edge node, thereby reducing the bandwidth overhead. Existing edge computing-based models optimize the performance, but they still have defects in three perspectives: 1) enabling end users to control video content in a real-time format; 2) efficiently locating and transferring the user region of interest (ROI) video data in the video stream; and 3) adapting to various network conditions. To tackle these challenges, we proposed an intelligent elastic edge framework for live video analytics, known as ElasticEdge. ElasticEdge enables the interaction between the end user and the edge node. Elasticity is reflected in two perspectives: 1) the dynamic changes of user requirements and 2) the dynamic changes in network conditions. In addition, ElasticEdge transmits the video stream to the end users based on the tradeoff between the amount of video data and users’ ROI to meet various network conditions. To validate ElasticEdge, we conducted experiments to study its performance in comparison to RTFace. The experimental results show that ElasticEdge has a significant edge over RTFace in terms of data transmission. Using 1/16 reserved images, ElasticEdge saves 75% bandwidth and reduces latency by approximately 10% compared with RTFace. We also find that ElasticEdge adapts to various network conditions when streaming videos, i.e., it can reliably obtain essential information with low latency even when the network condition is poor.

Deep neural network (DNN)-based video processing methods are applied in mobile video analytics because of high accuracy. Edge computing is an efficient paradigm that improves the performance of mobile video analytics. However, due to the limited computing and storage resources at edge devices, deploying DNN-based video analytics at edge devices may have difficulty to meet user’s requirements in terms of accuracy, delay, power consumption, and device costs. Choosing optimal system configuration, including resources on edge devices and parameters in video stream and DNN models, can better satisfy user’s performance requirements; however, there lacks practical approaches to find such optimal configurations. In this article, we take an initial step to investigate the optimal system configuration problem, and propose a data-driven approach, EdgeEye, which first models the above problem as a combinatorial optimization problem, and then designs an algorithm to find the solutions for the optimal configuration. These models and algorithms are applied in a real-world face detection and recognition application based on two edge computing models, including edge only and edge server. Comprehensive evaluation results demonstrate that EdgeEye can find both feasible and optimal system configurations including optimal edge computing model to satisfy varying user requirements under different network conditions.

With the large number of cameras deployed in smart industrial parks and smart campuses, edge devices and location-fixed edge servers are deployed near to these cameras and help transmit video streams to data center for video analytics; however, location-fixed edge servers are difficult to adapt to computation-intensive and delay-sensitive video analytics tasks in hot spot, and it is also challenging to execute tasks in natural disasters in which the infrastructure is damaged. Moreover, task migration methods are used to balance the load of edge servers caused by irregular movement of detected objects, but it results in extra data transmission overhead. Therefore, unmanned aerial vehicles (UAVs) with computing and communication resources are widely used to optimize mobile edge video analysis; however, existing solutions formulate the UAV-based lowest latency and energy consumption by jointly optimizing the task allocation strategy and UAV location to be a multiobjective optimization problem, based on which the Pareto optimum solution set, including task allocation strategies and UAV locations, can find multiple solutions but not a unique solution. It makes the solution difficult to be applied in video analytics with the UAV hover location decision-making scheme and task allocation strategy. In this article, we propose a flexible cloud-edge collaborative scheduling strategy based on a UAV namedFlexEdge. We first normalize values of execution time and energy consumption, and then convert the multiobjective optimization problem into a single-objective optimization problem by using the weighted sum of the two metrics as the optimization objective. We also proved the task allocation strategy based on execution time, energy consumption, and the UAV hover location decision-making scheme as an NP-hard problem. We propose a flexible and lightweight genetic algorithm (FGA) based on a polysomy-strengthening elitist genetic algorithm in FlexEdge to address the NP-hard problem. FlexEdge not only achieves optimal task allocation and UAV location to minimize the weighted sum of execution time and energy consumption but also provides computing resources and reliable network connection to reduce task offloading overload, which is validated by comprehensive performance evaluation.

Traffic context plays an important role in supporting automated driving and intelligent transportation systems. Smart vehicles explore surrounding environments by analyzing sensor data and periodically communicating with neighbors and road infrastructures. The context can be well learned in this way to support driving, but the vehicle trajectory can be also easily exposed under eavesdropping attacks. The pseudonym is proposed to hide the real identity of the vehicles. However, the effectiveness of anonymity, the safety of driving, the convenience of implementation and the utilization of resources in previous approaches have not been well-balanced. Therefore, focusing on efficiently replacing pseudonyms with the premise of ensuring driving safety, we propose a secure dynamic silent mix zone pseudonym changing scheme (TLAS) based on the real-time traffic context prediction for urban regions. It naturally takes the area in front of the red traffic light as a silent mix zone, which avoids the driving security issue caused by signal silence. Besides, the area length is dynamically configured according to the traffic context predicted in the last green light cycle, so the anonymous effect can be improved. In addition, considering the resource utilization and accuracy requirement, the adaptive prediction algorithm is applied. We conduct simulation experiments with real-world traffic history using SUMO and OMNET++, the results show that TLAS strategy can indeed achieve a better anonymous effect (reducing standardized traceability rate by 8.2%) with lower driving speed for safety concern.

Vehicular ad-hoc network (VANET) plays an extremely important role in future intelligent transportation systems. Many researchers proposed different schemes to improve communication efficiency under the premise that conditional privacy is preserved. In this paper, we propose an efficient conditional privacy-preserving authentication scheme using revocation messages to optimize VANET communication. Our scheme consists of two phases. First, in the anonymous identity generation and message signing phase, lightweight hash operations are used, and message length is reduced both the computation and communication overheads in VANET. Second, in the vehicle revocation phase, Road Side Units broadcast revocation messages to prevent malicious vehicles from generating anonymous identity and signing messages quickly. Security and performance analysis demonstrate that our proposed scheme is more secure and efficient than many existing schemes, and is more suitable for the deployment of VANET.

Software-defined Networking (SDN) brings new vitality to traditional network technology as its nice property of network programmability makes our network more open and flexible. By using interfaces of SDN controllers, different applications with diverse network functions can deploy their needed flow rules into SDN switches. However, some of these flow rules would probably produce conflicts that result in invalidation of network functions and cause security issues. To address this issue, we design a novel approach, Transaction-based flow rule Conflict Detection and Resolution (TCDR), which can isolate the flow rules of different network functions to avoid interference between different network functions. Meanwhile, our proposed method introduces a transaction-based authentication to guarantee the legality of flow rules. Finally, we implement a prototype of our solution, and evaluate its effectiveness and efficiency. The performance evaluation shows that TCDR can reject illegal flow rules and avoid many flow rule conflicts with a small overhead.

Although current proposed compression schemes achieve a better performance compared with traditional data compression schemes, they have not fully exploited the spatial and temporal correlations among the data. Well-designed clustering algorithms are needed to explore strong spatial correlation. In this paper, we propose a k-means based Kronecker supported two-dimensional (spatio-temporal) compression scheme to achieve better compression results. Our scheme first leverages a k-means based clustering algorithm that explores the spatial correlation among sensory data. Then it develops a novel two-dimensional data compression mechanism, which can recover the original data from the compressed data with a high precision. Simulation results show that our proposed scheme is energy-efficient and can achieve better clustering results and recovery performance compared with other schemes for sensory data.

The integration of the physical world and the cyber system in IoT brings significant challenges to the design of security solutions. Access control is considered to be a critical system component for the protection of data, cyberinfrastructure, and even the physical systems in IoT; however, because of the new characteristics of IoT systems, such as the resource constraints, the large scale and the device heterogeneity, many traditional security solutions including existing access control mechanisms may not be directly applicable in IoT environment. This paper first presents an overview of the existing access control mechanisms and analyzes their applicability in IoT systems. Then, both the challenges in the IoT access control design and the goals for future IoT access control design are identified and discussed.

With the widespread availability of connected smart devices, Internet of Things (IoT) is becoming the world's largest computing platform. These large-scale, heterogeneous and resource-constrained devices bring many significant new challenges to the design of efficient and reliable IoT systems. Security is one of the most crucial ones that need to be effectively addressed for the wide adoption of IoT systems. In this paper, we first present an in-depth analysis of security challenges in IoT. Then, we propose EdgeSec, the design of a novel security service which is deployed at the Edge layer to enhance the security of IoT systems. EdgeSec consists of seven major components that work together to systematically handle specific security challenges in IoT systems. Finally, the effectiveness of EdgeSec is demonstrated in the context of a typical IoT application, Smart Home.

Wireless sensor networks are widely applied in data collection applications. Energy efficiency is one of the most important design goals. In this paper, we propose QAAC, Quality-Assured Adaptive data Compression, to reduce the amount of data communication so that to save energy. QAAC first builds clusters from dataset using an adaptive clustering algorithm; then a code for each cluster is generated and stored in a Huffman encoding tree, which is used to encode the original dataset in an encoding algorithm with improvement approach. After the encoded data, the Huffman encoding tree and parameters used in the improvement algorithm have been received at the sink, a decompression algorithm is used to retrieve the approximation of the original dataset. The performance evaluation shows that QAAC is efficient and achieves much higher compression ratio than compared lossy and lossless compression algorithms and much less information loss than compared lossy compression algorithms.

Shortage of qualified cybersecurity workforce is a national problem. Without an effective solution, people's daily lives, business operations, and even national security are in jeopardy. Higher education institutions have invested in various approaches to train college students to acquire cybersecurity related knowledge, skills, and abilities. The existing approaches still need improvement and refinement and do not apply universally. In this paper, we report our efforts in designing and implementing a holistic framework for cybersecurity education with the desired level of breadth and depth. The framework is hierarchical since it includes all levels of cyber citizens especially in an organizational environment. The framework is also multi-facet to include various knowledge domains. These two characteristics of the framework make it modular and extensible, which allows progressive implementation. Implementation of this framework is currently underway at a small university where resources are limited. The framework is proven useful and practical, and can be adopted in a similar setting by other institutions.

Exercise is complementary to cancer prevention, care, and survivorship. Exercise is considered safe and effective during and after cancer treatment when conducted under supervision and in controlled environments. Less is known about the safety and effectiveness of unsupervised, home-based exercise programs. Implementing methods of monitoring and reporting can provide more information and potentially enhance exercise effects and program integrity. This paper describes the development of REMEDY, a remote monitoring sensor system consisting of a wireless body-area network (WBAN), cloud database, mobile assisted application, and a set of intelligent algorithms. REMEDY can provide real-time exercise monitoring, participant feedback, and quality assessment that may lead to safer and more effective exercise programs and exercises for cancer patients and survivors.

The information gradient-based routing protocols have been proved to be economical and effective by adopting the principle of achieving the global objective through local decision, but lightweight methods to construct the information gradient should be fully investigated, especially in a large-scale network with high information dynamics. In this paper, we focus on the construction of the information gradient by balancing convergence conditions and energy consumption. Therefore, two algorithms, Hierarchical Skeleton-based Construction Algorithm (HSCA) and Estimate value Substitution Algorithm (ESA) are proposed to achieve the goal of fastening the convergence in an energy efficient way. Both of the algorithms obey the typical assumptions on WSNs settings and the gossip-styled propagation principle. Comprehensive simulation results show that the proposed algorithms can reduce iteration times to reach a convergence status by 80% and conserve 30–50% energy consumption on average.

With wide deployments of Smart Grid systems, a large amount of energy usage and grid status data have been collected by smart meters. To secure those critical and sensitive data, it is crucial to prevent unauthorized readings to smart meters. Many authentication protocols have been proposed to control the access to the smart meters that are a part of Smart Grid data communication network, but authentication protocols to control readings to the isolated smart meters are mostly ignored. In this paper, we design a one-time symmetric key based cloud supported protocol to enable secure data reading from the isolated smart meters. The protocol mainly consists of two steps. First, an asymmetric key based authentication is designed for the reader-cloud authentication. Then, the cloud assists the meter reader to generate a new one-time symmetric key which is shared with the smart meter. Second, a symmetric key based authentication is designed for the reader-meter authentication. Security analysis shows that our protocol is reliable under most typical attacks.

For some sensor network applications, the problem of sweep coverage, which periodically covers POIs (Points of Interest) to sense events, is of importance. How to schedule minimum number of mobile sensors to achieve the sweep coverage within specified sweep period is a challenging problem, especially when the POIs to be scanned exceeds certain scale and the speed of mobile sensor is limited. Therefore, multiple mobile sensors are required to collaboratively complete the scanning task. When the mobile sensor is restricted to follow the same trajectory in different sweep periods, we design a centralized algorithm, MinExpand, to schedule the scan path. When the scan path of the existing mobile sensors has been exceeds the length constraint, MinExpand gradually deploys more mobile sensors and eventually achieves sweep coverage to all POIs. When the mobile sensors are not restricted to follow the same trajectory in different sweep periods, we design OSweep algorithm, where all the mobile sensors are scheduled to move along a TSP (Traveling Salesman Problem) ring consists of POIs. We conduct comprehensive simulations to study the performance of the proposed algorithms. The simulation results show that MinExpand and OSweep outperform CSWEEP in both effectiveness and efficiency.

In order to maximize the lifetime of wireless sensor networks, while ensuring the monitoring quality for specific applications, we develop the sleep-wakeup algorithms for the sensor networks. Firstly, for the three-dimensional wireless sensor networks, we formulate the virtual barrier coverage problems. Secondly, the design and implementation of the nodes sleep-wakeup scheduling algorithm, FWP, to maximize the covering time of a single virtual barrier and the k-virtual barriers sleep-wakeup scheduling algorithm, OBP, to maximize the network coverage time of k virtual barriers are presented. Finally, through the comprehensive simulation, the effectiveness of the algorithms is validated. The relationships among the density of the virtual barriers, virtual lattice point, the number of sensors and the sensing radius are also investigated and simulated.

Vehicular networks have attracted extensive attentions in recent years for their promises in improving safety and enabling other value-added services. Security and privacy are two integrated issues in the deployment of vehicular networks. Privacy-preserving authentication is a key technique in addressing these two issues. We propose a random keyset based authentication protocol that preserves user privacy under the zero-trust policy, in which no central authority is trusted with the user privacy. We show that the protocol can efficiently authenticate users without compromising their privacy with theoretical analysis. Malicious user identification and key revocation are also described

Prolonging the lifetime of wireless sensor networks (WSN) is one of the most important goals in the sensor network research. A lot of work has been done to achieve this goal; however, current definition of lifetime is either superficial or impractical. In this paper, we take the first step to modeling the lifetime of a wireless sensor network by considering the relationship between the whole sensor network and individual sensors, as well as the importance of different sensors based on their positions. We envision that the proposed lifetime model can be used to evaluate energy-efficient protocols and algorithms, which is validated by simulation results.