Article
Computer Science, Information Systems
Azizjon Meliboev, Jumabek Alikhanov, Wooseong Kim
Summary: In the modern era, studying Intrusion Detection Systems (IDS) is crucial for ensuring network security. Deep Learning (DL) is an essential tool for solving complex system problems. This work proposes an effective and adaptive IDS using DL methods, specifically utilizing architectures such as CNN, LSTM, RNN, and GRU. The experiments demonstrate that CNN and LSTM combination models outperform other models.
Article
Computer Science, Hardware & Architecture
Houda Jmila, Mohamed Ibn Khedher
Summary: Intrusion detection is a key topic in cybersecurity, and machine learning is widely used in this field. This paper investigates the robustness of shallow machine learning-based intrusion detection systems against adversarial attacks, and evaluates the performance of different classifiers under different attacks.
Article
Computer Science, Interdisciplinary Applications
Isra Al-Turaiki, Najwa Altwaijry
Summary: Cybersecurity is crucial for protecting and recovering computer systems and networks from cyber attacks as people rely more on technology. This article introduces two deep learning models using convolutional neural network architecture to classify network attacks, along with a hybrid two-step preprocessing approach. The models outperform similar approaches in terms of accuracy and recall, as shown in experimental results using benchmark datasets.
Article
Computer Science, Artificial Intelligence
Hadeel Alazzam, Ahmad Sharieh, Khair Eddin Sabri
Summary: This paper introduces an intelligent lightweight IDS with a low false alarm rate while maintaining a high detection rate. The proposed system is a fusion of two main subsystems that work in parallel, each trained on normal packets and attack packets, with the results combined to provide judgments for each packet passing through the network.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Amir Basati, Mohammad Mehdi Faghih
Summary: This paper presents a new and lightweight architecture for intrusion detection in IoT devices based on Parallel Deep Auto-Encoder (PDAE). By separating features using local and surrounding information, the accuracy of the model is improved while reducing the number of parameters and resource requirements. The effectiveness of the proposed model is evaluated and it outperforms state-of-the-art algorithms in terms of both accuracy and performance.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Wathiq Laftah Al-Yaseen, Ali Kadhum Idrees, Faezah Hamad Almasoudy
Summary: This paper proposes an efficient feature selection method for intrusion detection systems to reduce redundant and irrelevant features, improve system performance, and decrease processing time. The experiments demonstrate that the proposed method significantly enhances the accuracy and efficiency of IDS.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
P. Rajesh Kanna, P. Santhi
Summary: Recent advancements in information and communication technologies have led to a growing number of online systems and services. Therefore, it is necessary to design advanced and intelligent IDS models to ensure the trustworthiness of these systems. However, most existing IDS models based on traditional machine learning algorithms lack efficient feature selection and classification performance for new attacks. Additionally, they struggle with the recognition of known attacks and handling massive amounts of network traffic data. To address these issues, this paper presents an efficient hybrid IDS model built using the BWO-CONV-LSTM network. The model incorporates feature selection by the ABC algorithm and a hybrid deep learning classifier on a MapReduce framework. Performance evaluations demonstrate high intrusion detection accuracy and improved classification coefficients.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Chemistry, Multidisciplinary
Pierpaolo Dini, Abdussalam Elhanashi, Andrea Begni, Sergio Saponara, Qinghe Zheng, Kaouther Gasmi
Summary: The Intrusion Detection System (IDS) is an effective tool used in cybersecurity systems to detect and identify intrusion attacks. Feature selection is crucial to enhance performance, and the structure and balance of the dataset can impact the efficiency of the machine learning model. This research aims to explore ML approaches for IDS, focusing on datasets, machine algorithms, and metrics.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Amir Basati, Mohammad Mehdi Faghih
Summary: The use of IoT has increased significantly in recent years, making real-time cyber-threat protection crucial. However, current IoT devices are often lacking security features and are vulnerable to attacks. Therefore, it is important to develop tools for real-time attack detection in IoT networks. This paper proposes a new intelligent network intrusion detection system called APAE, which utilizes an asymmetric parallel auto-encoder to effectively detect various attacks in IoT networks.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Murtaza Ahmed Siddiqi, Wooguil Pak
Summary: This paper discusses the importance of intrusion detection in improving network security, the application in the field of machine learning, and the selection of suitable normalization methods for datasets.
Article
Computer Science, Information Systems
Mahzad Mahdavisharif, Shahram Jamali, Reza Fotohi
Summary: This article presents an efficient and effective Intrusion Detection System (IDS) using big data-aware deep learning method. By designing a specific architecture of Long Short-Term Memory (LSTM), the system can detect complex relationships and long-term dependencies in incoming traffic packets, reducing false alarms and increasing accuracy. Utilizing big data analytic techniques improves the speed of deep learning algorithms for detecting unauthorized access to communication networks.
JOURNAL OF GRID COMPUTING
(2021)
Article
Telecommunications
Lalit Kumar Vashishtha, Akhil Pratap Singh, Kakali Chatterjee
Summary: The cloud computing model is widely popular, but security is a major concern. This research introduces a hybrid intrusion detection model for cloud based systems, combining signature-based detection and anomaly-based detection to detect known and unknown attacks. The experiments show high detection rates for the proposed model compared to existing models.
WIRELESS PERSONAL COMMUNICATIONS
(2023)
Article
Mathematics
Iftikhar Ahmad, Qazi Emad Ul Haq, Muhammad Imran, Madini O. Alassafi, Rayed A. AlGhamdi
Summary: Intrusion detection in computer networks is important for communication and security domains, but remains a challenging task. This paper compares multiple techniques to develop a network intrusion detection system and proposes an AdaBoost-based approach. Experimental results show that the proposed method effectively detects different forms of network intrusions and achieves 99.3% accuracy on the UNSW-NB15 dataset.
Article
Green & Sustainable Science & Technology
Imran, Faisal Jamil, Dohyeun Kim
Summary: The article discusses an intrusion detection system based on the ensemble of prediction and learning mechanisms to improve anomaly detection accuracy in a network intrusion environment. The learning mechanism is based on automated machine learning, and the prediction model is based on the Kalman filter. Through performance analysis of the UNSW-NB15 and CICIDS2017 datasets, the proposed model-based intrusion detection accuracy is 98.801 percent for the UNSW-NB15 dataset and 97.02 percent for the CICIDS2017 dataset, showing significant improvement in intrusion detection accuracy with the proposed ensemble model.
Article
Computer Science, Information Systems
Gulab Sah, Subhasish Banerjee, Sweety Singh
Summary: The intrusion detection system (IDS) is crucial for extracting and analyzing network traffic to detect abnormal activity. However, emerging technologies generate large volumes of traffic that may contain irrelevant attributes. To address this issue, researchers have used feature selection approaches to remove non-relevant features and find important ones, and have investigated various classifiers to improve IDS performance.
INTERNATIONAL JOURNAL OF INFORMATION SECURITY
(2023)
Article
Engineering, Aerospace
Xin Sun, Baihai Zhang, Runqi Chai, Antonios Tsourdos, Senchun Chai
Summary: This article presents a novel approach for solving chance-constrained trajectory optimization problems in nonlinear dynamic systems. By transforming the chance constraints into deterministic ones and utilizing iterative convex optimization and successive linearization algorithms, feasible trajectory solutions are obtained.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Automation & Control Systems
Yihao Xu, Baihai Zhang, Senchun Chai, Yanqian Wang
Summary: This article investigates the problem of event-based resilient and robust H infinity control for semi-Markov jump systems (S-MJSs) under stochastic cyber attacks. The dynamic event-triggered (DET) scheme is adopted to reduce the total number of released data through the transmission channel and various factors such as actuator fault and signal quantization are taken into consideration. Based on the linear matrix inequality (LMI) approach, the sufficient conditions for stochastic stability of the system are derived and the co-design of resilient controller gains and weighting matrices is presented in terms of a group of feasible LMIs.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Automation & Control Systems
Dongyu Han, Kun Liu, Henrik Sandberg, Senchun Chai, Yuanqing Xia
Summary: This article discusses a distributed optimization problem with privacy concerns in multi-agent networks where malicious agents try to infer the privacy information of normal agents. A novel dual averaging algorithm is proposed that utilizes a correlated perturbation mechanism to protect the privacy of normal agents. It is proven that the algorithm achieves deterministic convergence under any initial conditions while guaranteeing privacy preservation. Furthermore, a probability density function for the perturbation is provided to maximize privacy measured by the trace of the Fisher information matrix. Lastly, a numerical example is presented to illustrate the effectiveness of the algorithm.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Automation & Control Systems
Runqi Chai, Antonios Tsourdos, Senchun Chai, Yuanqing Xia, Al Savvaris, C. L. Philip Chen
Summary: This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. It proposes a novel desensitized trajectory optimization method to provide an effective alternative for addressing the complexity of the mission formulation.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Yihao Xu, Senchun Chai, Peng Shi, Baihai Zhang, Yanqian Wang
Summary: This article investigates the resilient and event-triggered control problem of stochastic jump systems subject to randomly occurring denial of service (DoS) attacks and deception attacks. The proposed resilient and memory event-triggered scheme (RMETS) can effectively balance the desired security performance and limited network resources. By using the Lyapunov theory and the linear matrix inequality method, the resilient controller and the proposed RMETS are co-designed to ensure security performance under the two types of attacks. Numerical and practical examples are provided to illustrate the effectiveness of the developed approach.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Neurosciences
Liqun Huang, Enjun Zhu, Long Chen, Zhaoyang Wang, Senchun Chai, Baihai Zhang
Summary: In this paper, we propose a novel transformer-based generative adversarial network for automated brain tumor segmentation. By utilizing transformer blocks and Resnet in the generator, as well as incorporating multi-scale L-1 loss in the discriminator, our approach achieves promising performance in medical image segmentation tasks.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Huifang Li, Bing Chen, Jingwei Huang, Julio Ruben Canizares Abreu, Senchun Chai, Yuanqing Xia
Summary: In this study, a Mutation-driven and population Grouping Poor and Rich Optimization algorithm (MG-PRO) is proposed for scheduling workflows in the cloud. It aims to minimize makespan while satisfying budget constraints. Extensive experiments show that MG-PRO outperforms existing algorithms in terms of constraint satisfiability, solution quality, and stability.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Qirui Zhang, Kun Liu, Andre M. H. Teixeira, Yuzhe Li, Senchun Chai, Yuanqing Xia
Summary: This article investigates the design of online stealthy attacks, where the attacker estimates the system's state with intercepted data and computes the optimal attack accordingly. The Kullback-Leibler divergence is used to ensure stealthiness. The attacker should solve a convex optimization problem at each instant to compute the attack parameters.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
Article
Medicine, General & Internal
Nan Zhang, Xin Zhao, Jie Li, Liqun Huang, Haotian Li, Haiyu Feng, Marcos A. A. Garcia, Yunshan Cao, Zhonghua Sun, Senchun Chai
Summary: A fully automatic framework based on machine learning was developed for pulmonary artery pressure assessment using CTPA images. It accurately segmented the pulmonary artery and heart, and automatically assessed the PAP parameters. It has the ability to accurately distinguish different patients with pulmonary hypertension.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Automation & Control Systems
Haojun Wang, Kun Liu, Dongyu Han, Senchun Chai, Yuanqing Xia
Summary: This article investigates privacy-preserving distributed online stochastic optimization problem with random parameters following time-varying distributions. A method based on function decomposition is proposed to preserve the private subgradient information of each node, while ensuring privacy preservation and convergence accuracy. A privacy-preserving distributed online stochastic optimization algorithm is then proposed based on the primal-dual method. Numerical simulation results demonstrate the effectiveness of the proposed algorithm.
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS
(2023)
Article
Automation & Control Systems
Runqi Chai, Derong Liu, Tianhao Liu, Antonios Tsourdos, Yuanqing Xia, Senchun Chai
Summary: This paper presents an integrated real-time trajectory planning and tracking control framework for autonomous ground vehicles (AGV) parking maneuver problems, utilizing deep neural networks and recurrent network structures. Two transfer learning strategies are applied to adapt the motion planner for different AGV types. Experimental studies demonstrate enhanced performance in fulfilling parking missions.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Jun Li, Yuhan Suo, Senchun Chai, Yihao Xu, Yuanqing Xia
Summary: This paper focuses on the H-infinity resilient and event-triggered control of singular Markov jump systems against deception attacks. The event-triggered scheme achieves a balance between system performance and network resources, and the co-design of resilient controller gains and event triggered rules is provided.
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Xin Zhao, Tongming Wang, Jingsong Chen, Bingrun Jiang, Haotian Li, Nan Zhang, Guang Yang, Senchun Chai
Summary: This study proposes a novel contrastive learning strategy that leverages the relative position differences between image slices, combined with global and local features, to address the challenge of generating positive and negative data pairs for medical image segmentation. By employing a two-dimensional fully connected conditional random field for iterative optimization, segmentation accuracy is enhanced and isolated mis-segmented regions are reduced. Experimental results demonstrate that this method outperforms existing semi-supervised and self-supervised techniques in medical segmentation tasks with limited annotated samples.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2023)
Proceedings Paper
Automation & Control Systems
Mengyang Li, Senchun Chai, Tongming Wang, Baihai Zhang
Summary: The incidence rate of cardiovascular diseases has been increasing, with cardiac MRI being an important detection method. Existing heart segmentation methods require a large number of labeled datasets, which is time-consuming and laborious. This paper proposes a deep active learning method based on entropy, which is shown to outperform random sampling and only requires a small amount of labeled data.
2022 41ST CHINESE CONTROL CONFERENCE (CCC)
(2022)
Proceedings Paper
Automation & Control Systems
Zhaozhan Song, Senchun Chai, Enjun Zhu
Summary: In this paper, a multi-branch shape-aware segmentation network named CDM-Net is proposed based on 3D-UNet with spatial attention module. The traditional segmentation problem is transformed into a regression problem of distance transformation map and centerline heatmap. A new inference method based on regression is also introduced. Without changing other segmentation metrics, the proposed method improves the connectivity of aorta segmentation results.
2022 41ST CHINESE CONTROL CONFERENCE (CCC)
(2022)