Article
Computer Science, Information Systems
S. Velliangiri, N. G. Bhuvaneswari Amma, Nam-Kyun Baik
Summary: This paper proposes a statistical method for identifying DoS attacks in smart city networks, and develops a DoS attack detection model with low computational complexity and low false positive rate. Using smart city network traffic data set and feature distance map method for statistical analysis, this approach enhances the accuracy of attack detection.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Automation & Control Systems
Yanping Yang
Summary: This paper addresses the problem of average cluster synchronization control of networked harmonic oscillators under denial-of-service (DoS) attacks. A novel switching cluster synchronization control scheme is proposed, which selects different control protocols based on the occurrence of DoS attacks. The control design criteria for both synchronous and asynchronous DoS attacks are established using a Lyapunov-Krasovskii functional method. An iterative algorithm is designed to calculate the control gain matrices. The effectiveness of the proposed control scheme is demonstrated through a multi-vehicle cooperative control system.
Article
Computer Science, Information Systems
Mitali Sinha, Pramit Bhattacharyya, Sidhartha Sankar Rout, Neha Bhairavi Prakriya, Sujay Deb
Summary: The increasing use of third-party accelerators in modern SoCs can introduce vulnerabilities and lead to system attacks. To detect flooding attacks, we propose a two-step attack detection framework using machine learning, which achieves accurate detection with minimal performance impact.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Review
Computer Science, Information Systems
Aanshi Bhardwaj, Veenu Mangat, Renu Vig, Subir Halder, Mauro Conti
Summary: The cloud computing model offers organizations on-demand, elastic, and fully managed computer system resources and services. However, attacks on cloud components can result in significant losses for cloud service providers and users. DDoS attacks, including new attack vectors and strategies, have become more frequent and intense due to advancements in IoT and network connectivity. This survey aims to address the gaps between potential future DDoS attacks and current defensive solutions, highlighting the importance of comprehensive detection methods and the need for investment in DDoS detection mechanisms in the cloud environment.
COMPUTER SCIENCE REVIEW
(2021)
Article
Computer Science, Information Systems
Fangyuan Hou, Jian Sun, Qiuling Yang, Zhonghua Pang
Summary: This article investigates an optimal denial-of-service (DoS) attack scheduling problem for sensors with limited computational capability. A deep reinforcement learning (DRL) algorithm is introduced to solve the Markov decision process (MDP) for scheduling DoS attacks. Numerical examples are provided to demonstrate the effectiveness of the proposed approach.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Mathematics, Applied
Jin Guo, Ruizhe Jia, Ruinan Su, Yanlong Zhao, Yong Song
Summary: This paper focuses on the security problem of identifying Finite Impulse Response (FIR) systems with binary-valued observations under DoS attacks during transmission. Optimal attack strategies and encryption-type defense schemes are proposed from the perspectives of the attacker and defender, respectively. Numerical simulations are conducted to verify the effectiveness and correctness of the conclusions.
APPLIED MATHEMATICS AND COMPUTATION
(2023)
Article
Engineering, Electrical & Electronic
Yihua Yu, Yuan Liang
Summary: This paper presents a multisensor multitarget tracking algorithm against adversarial attacks, utilizing belief propagation. The algorithm evaluates the marginal posterior densities of target states based on factor graph for detection and estimation of multitarget states.
DIGITAL SIGNAL PROCESSING
(2022)
Article
Engineering, Electrical & Electronic
Kunpeng Pan, Yang Lyu, Quan Pan
Summary: This article investigates the formation control problem for multi-agent systems (MAS) under multi-channel denial-of-service (DoS) attacks. A distributed formation control protocol and a translation-adaptive method are proposed to achieve the desired formation and ensure system stability under DoS attacks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2022)
Article
Computer Science, Information Systems
Vinicius De Miranda Rios, Pedro R. M. Inacio, Damien Magoni, Mario M. Freire
Summary: This article introduces the potential threat of Low-rate Denial of Service (LDoS) attacks and provides a review of classifications, detection, and countermeasures. The article points out that LDoS attacks' stealth nature and lack of defense methods may result in greater damage than before.
Article
Automation & Control Systems
Zhiqiang Zuo, Xiong Cao, Yijing Wang, Wentao Zhang
Summary: This article investigates the consensus problem of multiagent systems subject to Denial-of-Service attacks from a control perspective. A distributed observer-based controller is proposed to reconstruct the agents' states, proving that consensus can still be achieved under DoS attacks. The article also addresses scenarios where DoS attacks simultaneously affect communication networks associated with the controller and the observer, providing a sufficient condition to maintain consensus performance of MASs. Numerical simulations are provided to illustrate the theoretical results.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Review
Multidisciplinary Sciences
Mohammed Ayub, Omar Lajam, Abdullatif Alnajim, Mahmood Niazi
Summary: This paper systematically reviews the literature on machine learning techniques used to address DDoS attacks, and finds considerable variations in the datasets used and modeling algorithms employed. Most studies evaluate performance using the accuracy metric. The results of this review can guide future studies towards more constructive methods for addressing the problem of DDoS attacks.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
An-Yang Lu, Guang-Hong Yang
Summary: This article investigates stability analysis for cyber-physical systems under denial-of-service attacks, providing necessary and sufficient conditions for closed-loop stability as well as more easily verifiable sufficient conditions, with an online monitoring strategy for stability.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Automation & Control Systems
Yanping Yang, Chen Peng, Qing-Long Han
Summary: This article presents a resilient control design for synchronization of multiple harmonic oscillators coupled via a vulnerable network suffering from denial-of-service (DoS) attacks. A resilient logical packet processor (RLPP) is proposed to design a distinct resilient distributed control protocol for each harmonic oscillator. Sufficient conditions on the duration and frequency of attacks are derived using complete-type Lyapunov-Krasovskii functionals (LKFs), and the gain matrix is designed through solving a set of linear matrix inequalities with an optimization algorithm. The proposed synchronization control scheme is applied to a representative model of the single-phase photovoltaic grid interconnection process, and numerical simulations demonstrate the effectiveness of the method.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Computer Science, Information Systems
Chun-Lei Zhang, Guang-Hong Yang, An-Yang Lu
Summary: This paper presents a solution to the problem of resilient observer-based control for cyber-physical systems under Denial-of-Service attacks, by introducing interval partition technique and linear matrix inequalities to reduce the conservatism in stability analysis, and providing a design strategy to improve the resilience against DoS. Numerical example demonstrates the effectiveness of the proposed method in tolerating more intensive DoS attacks.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Juan Fernando Canola Garcia, Gabriel Enrique Taborda Blandon
Summary: This document introduces an IDS/IPS system called Dique, which uses deep learning algorithm to detect and prevent DoS attacks. The system can display and classify packets in real time, and allows users to switch between IDS and IPS modes. Additionally, an offensive system Diluvio was developed to test the functionality of Dique.
Article
Engineering, Electrical & Electronic
Bhuvaneswari N. G. Amma, Jitaksh Kapoor
Summary: Security of data is crucial in our digitized world, and a novel approach using encryption and LSB embedding to hide sensitive information without loss of quality has been proposed.
IETE JOURNAL OF RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
N. G. Bhuvaneswari Amma, S. Selvakumar
Summary: This article introduces an optimized deep neural network structure for detecting DDoS attacks, using the CuI optimization technique. Experimental results show that this optimization method outperforms existing techniques and achieves significant performance improvement.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Telecommunications
S. Priya, S. Selvakumar, R. Leela Velusamy
Summary: The increased use of wireless handheld devices and smartphones has led to a rise in internet phishing attacks. Phishing attacks involve forged websites that aim to obtain personal credentials from online users. Current methods for mitigating these attacks include black lists, white lists, and heuristic techniques, with the latter outperforming the others in detecting unknown attacks. Associative Classification (AC) is an emerging heuristic technique that utilizes Association Rule Mining for classification. However, existing AC techniques require two threshold values and face a sharp boundary problem due to discretization of quantitative attributes. To address these issues, this paper proposes a novel Particle Swarm Optimization based Fuzzy Associative Classifier (PaSOFuAC) for phishing website detection. The proposed approach improves detection accuracy by determining the best rule based on Rule Gain Ratio and utilizing fuzzy logic to overcome the sharp boundary problem. Experimental results demonstrate that PaSOFuAC outperforms existing techniques for detecting phishing websites.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
N. G. Bhuvaneswari Amma
Summary: This paper proposes a method for detecting cyber attacks using deep learning techniques. By using the Vector Convolutional Deep Autonomous Learning (VCDAL) classifier, unknown attacks can be detected in real time, and significant results have been achieved in experiments.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
E. Elakkiya, S. Selvakumar
Summary: In the past decade, the popularity and fascination for social networks have grown exponentially, leading to cybercriminals exploiting social networks for malicious activities such as spam. This research proposes the use of a feed-forward neural network for spam detection, utilizing a reinforcement learning and shuffled frog leaping algorithm to optimize the neural network parameters. Experimental results show that the proposed algorithm achieves higher accuracy and lower false positive rate compared to existing techniques.
Article
Engineering, Electrical & Electronic
Nageswari N. G. Amma, Bhuvaneswari N. G. Amma
Summary: The text discusses an authentication mechanism based on fingerprint biometrics, optimizing the extraction of unique points using partition clustering for higher uniqueness and security. The proposed mechanism, PClusBA, uses a cluster count of eight to achieve a 192-bit UID in accordance with NIST standards, and was found to provide unique results for each image tested.
IETE JOURNAL OF RESEARCH
(2022)
Article
Computer Science, Information Systems
Bhuvaneswari Amma Narayanavadivoo Gopinathan, Velliangiri Sarveshwaran, Vinayakumar Ravi, Rajasekhar Chaganti
Summary: This article suggests a method for anomaly detection in IoT networks to protect smart devices from cyberattacks. By selecting an optimal set of IoT traffic features and using a learning algorithm for classification, efficient detection at the edge of the IoT network can be achieved. The proposed approach utilizes a layered paddy crop optimization algorithm for feature selection and employs a capsule network for labeling traffic as normal or attack. The experimental results demonstrate the effectiveness of the proposed strategy, outperforming existing base classifiers and feature selection approaches.
Article
Computer Science, Information Systems
N. G. Bhuvaneswari Amma, Vikrant Rajput
Summary: Nowadays, autonomous vehicles are evolving with the advancements in cutting edge technologies. Traffic recognition system is required to efficiently recognize traffic signals. It consists of sign detection and classification. The proposed approach utilizes a support vector machine based fast detection module to detect traffic signs into different traffic classes, and deep convolutional neural networks for further classification into subclasses. Experimental results on benchmark traffic sign image datasets demonstrate that the proposed approach significantly improves traffic sign recognition accuracy compared to state-of-the-art systems.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
S. Velliangiri, N. G. Bhuvaneswari Amma, Nam-Kyun Baik
Summary: This paper proposes a statistical method for identifying DoS attacks in smart city networks, and develops a DoS attack detection model with low computational complexity and low false positive rate. Using smart city network traffic data set and feature distance map method for statistical analysis, this approach enhances the accuracy of attack detection.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Proceedings Paper
Computer Science, Information Systems
N. G. Bhuvaneswari Amma, P. Valarmathi
Summary: The evolution of technology has led to an increase in cyberattacks on IoT devices. Statistical methods can be used to detect intrusions in IoT traffic, but current techniques suffer from the curse of dimensionality. To address this issue, a method called IoT Intrusion Detection (IoTInDet) is proposed, which identifies intrusions by selecting relevant features and calculating their correlation.
INFORMATION SYSTEMS SECURITY, ICISS 2022
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Kanchana Rajaram, Arti Devi, S. Selvakumar
Summary: Recognition of children's palmprints has gained attention, and the use of CNN transfer learning for palmprint recognition is proposed in this paper. The results demonstrate the effectiveness of the approach with a high matching accuracy of 96% and a low Equal Error Rate (EER) of 0.02%.
MACHINE LEARNING AND AUTONOMOUS SYSTEMS
(2022)
Article
Computer Science, Information Systems
S. Priya, S. Selvakumar
Summary: This study introduces a method for detecting phishing attacks using a probabilistic neural network and a novel training algorithm, as well as a new clustering algorithm and optimization procedure to improve detection accuracy and reduce false positive rates.
INTERNATIONAL JOURNAL OF AD HOC AND UBIQUITOUS COMPUTING
(2021)