Article
Computer Science, Information Systems
Parminder Singh, Avinash Kaur, Gagangeet Singh Aujla, Ranbir Singh Batth, Salil Kanhere
Summary: This article introduces the Dew Computing as a Service (DaaS) for intelligent intrusion detection in Edge of Things (EoT) ecosystems. It uses a deep learning-based classifier to design an intelligent alarm filtration mechanism. The experimentation in a simulated environment shows lower response time, improved classification accuracy, and reduced workload of cloud servers compared to edge IDS.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Sergio Ruiz-Villafranca, Jose Roldan-Gomez, Javier Carrillo-Mondejar, Juan Manuel Castelo Gomez, Jose Miguel Villalon
Summary: New management methods in Industry 4.0 or IIoT integrate emerging technologies like IoT, DL, and ML to improve industrial applications and processes. However, the increasing threats and vulnerabilities in IIoT call for the development of new solutions. This paper proposes an intelligent threat detector based on boosted tree algorithms, which has been implemented and evaluated with a high mean efficiency of 95%-99% in the F1 Score metric.
Article
Chemistry, Multidisciplinary
Ruikui Ma, Qiuqian Wang, Xiangxi Bu, Xuebin Chen
Summary: With the rapid development of the Internet of Things (IoT), network traffic is increasing exponentially due to a vast number of connected devices. This has led to a rise in Distributed Denial of Service (DDoS) attacks, which are becoming larger in scale and easier to launch. To address this, a distributed DDoS attack detection algorithm using feature selection and random forest is proposed in this paper. The algorithm is deployed on SDN edge switches for fast and accurate detection of DDoS attacks, leveraging the residual computing power of the switches. Experimental results demonstrate that the proposed solution outperforms other methods in terms of accuracy, precision, recall, and F-value, with a prediction time of only 0.4 seconds.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Omar A. Alzubi, Jafar A. Alzubi, Moutaz Alazab, Adnan Alrabea, Albara Awajan, Issa Qiqieh
Summary: Fog computing introduces edge computing with limited resources, but processing large amounts of data and ensuring network security pose challenges. This study proposes the ESOML-IDS model, which combines feature selection and machine learning to improve intrusion detection efficiency and effectiveness.
Article
Computer Science, Hardware & Architecture
Gianmarco Lia, Marica Amadeo, Giuseppe Ruggeri, Claudia Campolo, Antonella Molinaro, Valeria Loscri
Summary: In this work, ML algorithms are used to orchestrate the placement of delay-constrained computing tasks in a softwarized edge domain. Among the compared techniques, Decision Tree and Multi-Layer Perceptron are shown to be the most efficient solutions in terms of algorithm execution time.
Article
Computer Science, Information Systems
Yixuan Wu, Laisen Nie, Shupeng Wang, Zhaolong Ning, Shengtao Li
Summary: With the rapid growth of IoT, cloud-centric computing struggles to meet the low latency and ease of use requirements. Edge computing, as an open and distributed system, integrates computing, networking, storage, and applications, providing intelligent services at the IoT edge. However, the edge network faces various cyber attacks due to its limited resources, making large-scale data collection and detection for IoT security challenging. This paper proposes an intelligent intrusion detection algorithm based on big data mining and a combination of fuzzy rough set, GAN, and CNN, achieving higher accuracy than existing methods.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Telecommunications
Fenghui Zhang, Ruilong Deng, Xinsheng Zhao, Michael Mao Wang
Summary: The paper investigates the improvement of service quality in edge computing by introducing artificial intelligence, and proposes a state-based distributed learning algorithm to balance the load of distributed intelligent edge servers. The convergence of the algorithm is proved, demonstrating significant enhancement in load balancing and service performance for the distributed IESs compared to existing works.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2021)
Article
Computer Science, Information Systems
Kun Yang, Peng Sun, Dingkang Yang, Jieyu Lin, Azzedine Boukerche, Liang Song
Summary: The focus of this research is to effectively coordinate the limited computing power of various components in intelligent transportation systems (ITS) and provide reliable support for resource-intensive applications through efficient resource allocation methods in the highly dynamic Internet-of-Vehicles environment. A novel joint computing and communication resource scheduling method is proposed, which includes a hierarchical three-layer Vehicular Edge Computing (VEC) framework and onboard joint computation offloading and transmission scheduling policy. Extensive simulation tests and ablation experiments demonstrate the effectiveness and stability of the proposed method in achieving stable performance and reducing scheduling overhead, improving resource utilization, and minimizing data transmission delay caused by vehicle motion.
Article
Computer Science, Artificial Intelligence
Gauri Kalnoor, S. Gowrishankar
Summary: The proposed work aims to design an intelligent intrusion detection system using machine learning models to identify and protect IoT networks from attacks. Experimental results show that the Markov model performs well in the I-IDS IoT network, achieving a 100% detection rate and low false alarm rate.
Article
Computer Science, Artificial Intelligence
Ashish Singh, Kakali Chatterjee, Suresh Chandra Satapathy
Summary: The security of the Mobile Edge Computing (MEC) model is a major challenge, with existing intrusion detection solutions unable to identify new unknown attacks. There is a need for an Edge-based Hybrid Intrusion Detection Framework (EHIDF) that can detect known and unknown attacks in real time with a low False Alarm Rate (FAR).
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Information Systems
Hui Sun, Qiyuan Li, Kewei Sha, Ying Yu
Summary: Cloud computing and edge computing models are widely used in emerging applications, but existing edge computing-based models have issues in user control, region of interest transmission, and adapting to network conditions. In order to address these challenges, we propose the ElasticEdge framework and validate its superiority over RTFace in terms of data transmission and adaptability to different network conditions.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Civil
Chen Chen, Bin Liu, Shaohua Wan, Peng Qiao, Qingqi Pei
Summary: This article presents a traffic flow detection scheme based on deep learning at the edge node, which efficiently addresses traffic congestion and environmental pollution issues. By optimizing vehicle detection and multi-object tracking algorithms, and deploying them on edge devices, real-time traffic flow detection is achieved.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2021)
Article
Computer Science, Hardware & Architecture
Earum Mushtaq, Aneela Zameer, Rubina Nasir
Summary: Cyber-attacks pose a threat to national security and hinder the beneficial utilization of the internet due to the pervasiveness of malware and cyber terrorism. This study proposes an auto-encoder and gated recurrent unit (GRU) based intrusion detection system (AE-GRU) to accurately, efficiently, and precisely classify network traffic.
Article
Engineering, Electrical & Electronic
Huan Wu, Chao Shang, Kun Zhu, Chao Lu
Summary: This study proposes a model to quantify the relationship between signal-to-noise ratio (SNR) and detection performance, providing a method for setting the decision threshold. Experimental validation shows that the autocorrelation-energy-based method achieves high detection probability and low false alarm probability in a DAS system.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Review
Computer Science, Information Systems
Jyoti Verma, Abhinav Bhandari, Gurpreet Singh
Summary: This article reviews the advancements in intrusion detection field in the last five years and conducts a comprehensive SWOT analysis of contemporary Network Intrusion Detection Systems in multiple technology dimensions. The authors have performed a comprehensive SWOT analysis of contemporary Network Intrusion Detection Systems, including big-data processing of high volume network traffic, machine learning, deep learning for self-learning machines, readiness for zero-day attacks, distributed processing, cost-effective solution, and ability to perform autonomous operations.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Guangquan Xu, Wenqing Lei, Lixiao Gong, Jian Liu, Hongpeng Bai, Kai Chen, Ran Wang, Wei Wang, Kaitai Liang, Weizhe Wang, Weizhi Meng, Shaoying Liu
Summary: To defend against Use-After-Free (UAF) exploits, a fine-grained memory permission management scheme called UAF-GUARD is proposed, which effectively defends against all types of UAF exploits and accurately locates the vulnerabilities.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Artificial Intelligence
Chengyi Qin, Lei Wu, Weizhi Meng, Zihui Xu, Su Li, Hao Wang
Summary: The outbreak of COVID-19 has brought attention to the privacy concerns of positive patients. A privacy-preserving scheme is proposed to address these concerns. By utilizing blockchain and local differential privacy, the proposed scheme enhances data accuracy, reduces computational overhead, improves storage performance, and ensures fairness.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jingkang Yang, Xiaobo Yu, Weizhi Meng, Yining Liu
Summary: In this study, a dummy trajectory generation scheme with conditional generative adversary network (GAN) is proposed to address the challenges of modeling map background information and generating high-quality dummy trajectories similar to real ones. Experimental results demonstrate the effectiveness of the proposed scheme in protecting the privacy of mobile users' locations and defending against various attacks.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Wenjuan Li, Jiao Tan, Nan Zhu
Summary: Smartphones are essential and widely used electronic devices due to their advanced features, providing benefits such as online shopping, e-commerce payment, social media connections, and email checking. However, securing locally stored phone data is a major concern, and using behavioral features in unlock mechanisms can be a promising solution.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Information Systems
Wenjuan Li, Yu Wang, Jin Li
Summary: Blockchain-enabled collaborative intrusion detection system provides an effective solution for securing cyber-physical systems by ensuring immutable data sharing without the need for a trusted third party.
INTERNATIONAL JOURNAL OF INFORMATION SECURITY
(2023)
Editorial Material
Computer Science, Information Systems
Weizhi Meng, Sokratis K. Katsikas, Jiageng Chen, Chao Chen
INTERNATIONAL JOURNAL OF NETWORK MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Yuan Chang, Jiliang Li, Wenjuan Li
Summary: This paper proposes a demand-driven privacy-preserving scheme for anonymous data sharing in smart grids, which solves the problems of controlled anonymity and fine-grained access control in existing data aggregation approaches.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Wenjuan Li, Christian Stidsen, Tobias Adam
Summary: A collaborative intrusion detection system (CIDS) is crucial for protecting decentralized computing platforms such as smart cities and IoT networks. Traditional CIDS often rely on centralized computing servers, which compromises the integrity of shared information. Blockchain technology provides a solution to this problem and has shown promising benefits in CIDS. This work introduces a blockchain-assisted security management framework for CIDS, demonstrating its effectiveness in both simulated and real CIDS setups.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Automation & Control Systems
Wei-Yang Chiu, Weizhi Meng, Chunpeng Ge
Summary: The advancement of information technology in Industry 4.0 allows for the creation of programmable smart devices that can perform machine-to-machine communication. However, the increased connectivity also increases the risk of cybercriminals sabotaging the execution integrity of these devices, leading to financial loss and malfunctioning. This article proposes a blockchain-based execution protection scheme called NoSneaky, which aims to secure the execution integrity of smart devices in a low-cost and easily integrated manner. Evaluation results demonstrate the effectiveness and performance of this blockchain solution.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Zuchao Ma, Liang Liu, Weizhi Meng, Xiapu Luo, Lisong Wang, Wenjuan Li
Summary: With the rise of cyber attacks, NIDS has become an essential tool for protecting IoT environments. However, the effectiveness of the detection model is crucial for NIDS performance, and it can be influenced by the learning mechanism and training data. To address these challenges, we propose a collaborative learning-based framework called ADCL, which leverages multiple models trained in similar environments to improve detection performance in IoT networks.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Proceedings Paper
Computer Science, Information Systems
Johan Hagelskjar Sjursen, Weizhi Meng, Wei-Yang Chiu
Summary: In the current literature, various solutions to blockchain scaling have been attempted, but most of them compromise decentralization. Ethereum has opted to scale through adopting Proof of Stake consensus and introducing data sharding to enable cheaper Layer 2 execution. However, the strategy may still contain centralizing forces due to cross-domain Maximal Extractable Value (MEV). This study focuses on cross-domain MEV and aims to identify cross-domain arbitrage by extracting Uniswap data from four domains and providing an initial analysis.
2023 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY, ICBC
(2023)
Proceedings Paper
Computer Science, Hardware & Architecture
Wei-Yang Chiu, Weizhi Meng, Wenjuan Li
Summary: Ensuring the authenticity of system communication and data preservation is crucial for a well-operated information system. While Blockchain enhances IoT security, it does not guarantee that each on-chain transaction is authorized. Stolen wallets can lead to financial loss for owners and questionable actions, creating difficulties in identifying transaction authenticity. TPMWallet is a blockchain-based hardware wallet that provides a secure subsystem, offering more functionality and increased difficulty for attackers.
2023 INTERNATIONAL CONFERENCE ON COMPUTING, NETWORKING AND COMMUNICATIONS, ICNC
(2023)
Article
Computer Science, Theory & Methods
Zixuan Wang, Jiliang Li, Yuntao Wang, Zhou Su, Shui Yu, Weizhi Meng
Summary: This paper proposes a novel game-theoretical approach for APT defense, aiming to achieve real-time and optimal defense strategy-making under both periodic time-varying and general time-varying environments. By modeling the interactions between attackers and defenders as a dynamic APT repair game and employing an online optimal control-based mechanism integrated with backtracking-forward algorithms, the near-optimal solution of the APT damage minimization problem can be derived in real time. Experimental results demonstrate the efficient performance of the proposed scheme in obtaining optimal defense strategies and its superiority over existing approaches even in static networks.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Telecommunications
Yuanyuan Zhang, Lingzhe Meng, Mingwu Zhang, Weizhi Meng
Summary: This research proposes a lightweight authentication scheme that supports batch authentication of multiple drones, improving efficiency and security of authentication. Batch authentication is achieved using hash function and point multiplication, and physical unclonable functions are introduced to resist physical attacks. Security analyses demonstrate the scheme's resilience against known attacks, and experimental results show better security and lower overheads compared to existing schemes for authenticating multiple drones.
VEHICULAR COMMUNICATIONS
(2023)
