Sándor Répás

55811595800

Publications - 20

Performance Analysis of Encryption Capabilities of ARM-based Single Board Microcomputers

Sándor Répás

Publication Name: Infocommunications Journal

Publication Date: 2023-06-01

Volume: 15

Issue: 2

Page Range: 8-13

Description:

In the few years since the Raspberry Pi was released in 2012, countless microcomputers based on the ARM architecture have been introduced. Their small size, high performance relative to their power consumption, and the ability to run the popular Linux operating system make them ideal for a wide range of tasks. Information security is an area of particular importance. Different encryption and encoding algorithms play an important role in almost all areas of information security. However, these algorithms are very computationally intensive, so it is important to investigate which microcomputers can be used for these tasks, and under which trade-offs. The performance of ten different microcomputers is investigated and presented for the application of common symmetric and public-key encryption and decryption, digest creation and message authentication protocols, such as RSA, AES, HMAC, MD5, SHA. Reliable encryption requires the generation of reliable (pseudo)random numbers (Cryptographically Secure Random Numbers, CSRN), and microcomputers based on ARM SoCs usually have hardware implemented (pseudo)random number generators. The applicability of the random number generators of different microcomputers are investigated and presented; test methods are described, and recommendations are made.

Open Access: Yes

DOI: 10.36244/ICJ.2023.2.6

Performance analysis and comparison of four DNS64 implementations under different free operating systems

Sándor Répás Gábor Lencse

Publication Name: Telecommunication Systems

Publication Date: 2016-12-01

Volume: 63

Issue: 4

Page Range: 557-577

Description:

The depletion of the global IPv4 address pool made the deployment of IPv6, the new version of the Internet Protocol, inevitable. In this paper, the transition mechanisms for the first phase of IPv6 deployment are surveyed and the DNS64 plus NAT64 solution is found appropriate. The most important free and open source DNS64 implementations are selected: BIND, TOTD, Unbound and PowerDNS. The test environment and the testing method are described. The first three of the selected DNS64 implementations are tested under Linux, OpenBSD and FreeBSD whereas PowerDNS is tested only under Linux. Their performance characteristics (response time, number of answered requests per second, CPU and memory consumption) are measured and compared. The effect of the hardware architecture of the test computer is also examined by using single-core, dual-core and quad-core test computers. The stability of all the tested DNS64 solutions are analyzed under overload conditions to test if they may be used in production environments with strong response time requirements. Our measurement results show significant differences in the performance of the tested DNS64 implementations, e.g. Unbound served four times more requests per second than PowerDNS (when executed by a single-core CPU under Linux and load was generated by eight clients). However, no absolute order can be determined, because it is influenced by different factors such as the architecture of the hardware, especially the number of cores, because BIND and PowerDNS are multithreaded (therefore they can profit from the multiple cores) but TOTD and Unbound are not. Also the operating system of the DNS64 server has significant influence on the performance of the DNS64 implementations under certain conditions. All the details of our measurements are disclosed and all the results are presented in the paper. An easy-to-use implementation selection guide is also provided as a short summary of our high number of results.

Open Access: Yes

DOI: 10.1007/s11235-016-0142-x

Stability analysis and performance comparison of five 6to4 relay implementations

Sándor Répás Viktor Horváth Gábor Lencse

Publication Name: Infocommunications Journal

Publication Date: 2016-06-01

Volume: 8

Issue: 2

Page Range: 1-10

Description:

Even though the present form of IPv6 has been existing since 1998, the adoption of the new protocol has been very slow until recently. To help the adoption of the IPv6 protocol, several transition technologies were introduced. The 6to4 protocol is one of them, and it can be used when an IPv6 enabled host resides in an IPv4 only environment and needs to communicate with other hosts in such circumstances or with native IPv6 hosts. Five open source 6to4 relay implementations were investigated: Debian Linux - sit, Debian Linux - v4tunnel, OpenWrt - sit, FreeBSD - stf, NetBSD - stf. The measurement method is fully described including our measurement scripts and the results of the measurements are disclosed in detail. The measurements have shown that there are major differences between the different types of implementations.

Open Access: Yes

DOI: DOI not available

Stability analysis and performance comparison of three 6to4 relay implementations

Sándor Répás Viktor Horváth Gábor Lencse

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: 82-87

Description:

During the IPv6 deployment there is a frequently occurring situation where two IPv6 enabled hosts need to communicate with each other over a network that supports only IPv4. Application of the 6to4 IPv6 transition method can solve this problem. The performance and stability of the different 6to4 relay implementations is a very important subject. We measured the performance and tested the stability of three open source 6to4 relay implementations under Debian Linux, OpenBSD and OpenWRT platforms. We present and discuss our results, analyze the stability of the 6to4 relay implementations and compare their performance metrics. Our measurements methods may be useful for other researchers, and our results may help the system architects to choose the appropriate solution.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296228

Method for benchmarking single board computers for building a mini supercomputer for simulation of telecommunication systems

Sándor Répás Gábor Lencse

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: 246-251

Description:

Parallel Discrete Event Simulation (PDES) with the conservative synchronization method can be efficiently used for the performance analysis of telecommunication systems because of their good lookahead properties. For PDES, a cost effective execution platform may be built by using single board computers (SBCs), which offer relatively high computation capacity compared to their price or power consumption and especially to the space they take up. A benchmarking method is proposed and its operation is demonstrated by benchmarking six different SBCs, namely Banana Pi, Beaglebone Black, Cubieboard2, Odroid-U3+, Radxa Rock Lite and Raspberry Pi Model B+. Their benchmarking results are compared to find out which one should be used for building a mini supercomputer for parallel discrete-event simulation of telecommunication systems. The SBCs are also used to build a heterogeneous cluster and the performance of the cluster is tested, too.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296261

Port number consumption of the NAT64 IPv6 transition technology

Sándor Répás Tamas Hajas Gábor Lencse

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Due to the depletion of the global IPv4 address pool, the internet service providers will be able to supply their new clients with IPv6 addresses only in the near future. The application of the DNS64 and NAT64 technologies can enable the IPv6 only clients to communicate with the still dominant IPv4 only servers. However, the clients of certain applications such as HTTP and FTP use multiple sessions and thus they consume multiple ports. This phenomenon may cause a lack of ports situation at the NAT64 gateway. Therefore the port consumption of the different applications is an important design parameter of the NAT64 gateways. In this paper, the port consumption of different NAT64 compatible applications was measured. It was also determined what factors can influence the port consumption of a web or an ftp client. The detailed description of our measurement method is given. Our results can give a valuable help for careful design and configuration of a NAT64 gateway.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296411

Application compatibility of the NAT64 IPv6 transition technology

Sándor Répás Tamas Hajas Gábor Lencse

Publication Name: 2015 38th International Conference on Telecommunications and Signal Processing Tsp 2015

Publication Date: 2015-10-09

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The proliferation of smart phones and other Internet capable devices together with the depletion of the global IPv4 address pool will be a huge driving force for the deployment of IPv6 in the forthcoming years. The communication of an IPv6 only client with an IPv4 only server is a typical practical task to be solved among the many issues of the co-existence of IPv4 and IPv6. The usage of DNS64+NAT64 may be a good solution if our applications can flawlessly work with it. As for NAT64 implementations, TAYGA running under Linux and Packet Filter (PF) of OpenBSD were tested with the following application level protocols: HTTP, HTTPS, SMTP, POP3, IMAP4, Telnet, SSH, FTP, OpenVPN, RDP, Syslog, BitTorrent, Skype and SIP. The client-server application protocols could traverse through the NAT64 gateway flawlessly but the peer to peer ones failed. In contrast to the results of other researchers, OpenVPN worked perfectly with NAT64.

Open Access: Yes

DOI: 10.1109/TSP.2015.7296383

Performance analysis and comparison of the TAYGA and of the PF NAT64 implementations

Sándor Répás Gábor Lencse

Publication Name: 2013 36th International Conference on Telecommunications and Signal Processing Tsp 2013

Publication Date: 2013-10-21

Volume: Unknown

Issue: Unknown

Page Range: 71-76

Description:

The transition mechanisms for the first phase of IPv6 deployment are surveyed and the most important NAT64 solutions are selected. The test environment and the testing method are described. As for the selected NAT64 implementations, the performance of the TAYGA running under Linux and of the Packet Filter (PF) of OpenBSD was measured and compared. The stability of the tested NAT64 solutions was analyzed under serious overload conditions to test if they may be used in production environments with strong response time requirements. © 2013 IEEE.

Open Access: Yes

DOI: 10.1109/TSP.2013.6613894

Performance analysis and comparison of different DNS64 implementations for Linux, OpenBSD and FreeBSD

Sándor Répás Gábor Lencse

Publication Name: Proceedings International Conference on Advanced Information Networking and Applications AINA

Publication Date: 2013-08-08

Volume: Unknown

Issue: Unknown

Page Range: 877-884

Description:

The transition mechanisms for the first phase of IPv6 deployment are surveyed and the most important DNS64 solutions are selected. The test environment and the testing method are described. As for the selected DNS64 implementations, the performance of both BIND9 and TOTD running under Linux, OpenBSD and FreeBSD are measured and compared. The stability of all the tested DNS64 solutions was analyzed under serious overload conditions to test if they may be used in production environments with strong response time requirements. © 2013 IEEE.

Open Access: Yes

DOI: 10.1109/AINA.2013.80

DDOS Attack Mitigation Based on FPGA Implementation

Sándor Répás Ahmed Jamal Ibrahim Ahmed Jamal Ibrahim

Publication Name: International Conference on Electrical Computer and Energy Technologies Icecet 2024

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

With the widespread use of computer networks daily, network security has become a significant problem in the new technology era. Due to the quick growth of the World Wide Web, it is becoming more challenging for researchers to find new methods to prevent attackers from reaching their targets. The spread of malicious cyber network activity poses a significant risk to numerous organizations and inflicts substantial economic consequences on society. Distributed Denial of Service (DDoS) is a cyberattack technique that disrupts the regular traffic of the target server or system by flooding it with an abnormal flow of internet traffic from different sources. The current article explores the advantages of FPGA-based devices in network security to mitigate the effects of DDoS attacks.

Open Access: Yes

DOI: 10.1109/ICECET61485.2024.10698517

The Impact of Diverse Gateway Implementations on Mesh Network Performance

Jitka Komarkova Tawfik Al-Hadhrami Sándor Répás Ibrahim Alameri Ahmed Jamal Ibrahim Elmustafa Sayed Ali

Publication Name: Lecture Notes on Data Engineering and Communications Technologies

Publication Date: 2026-01-01

Volume: 263

Issue: Unknown

Page Range: 27-38

Description:

Wireless Mesh Networks (WMNs) provide seamless connectivity in rapidly changing and dense environments. But when gateways are integrated to provide network access from outside the current topology, several issues become problems. These include maintaining high levels of performance, energy efficiency, security awareness and interconnection. Traditional routing protocols such as Ad hoc On-Demand Distance Vector Routing (AODV) were not able to achieve these two purposes at all in a hybrid setting where efficient communication with the gateway was needed, especially when faced with high mobility, node density and changing traffic loads. This paper introduces that the problem can be resolved by implementing Fuzzy Control Energy Efficient (FCEE) routing in WMNs The FCEE routing method, characteristic innovative energy-efficient real-time failure mechanism and overall network performance enhancement for wireless mesh networks By integrating fuzzy logic into the AODV framework, the FCEE method adds a short-term memory module that optimizes packet broadcasts based on real-time levels of energy available to each node. The FCEE method not only enhances decision-making for packet forwarding but also reduces unwanted broadcasts thus extending the life of the entire network. Simulations show the FCEE performs better than traditional methods in terms of both energy efficiency, congestion control, and adaptability to dynamic situations. The proposed method thus provides an affordable way to improve the operation of wireless mesh networks, particularly in the case of high traffic areas or long periods where resources are constrained.

Open Access: Yes

DOI: 10.1007/978-3-032-01005-6_3

Application of FPGA Devices in Network Security: A Survey

Sándor Répás Abdulmunem A. Abdulsamad

Publication Name: Electronics Switzerland

Publication Date: 2025-10-01

Volume: 14

Issue: 19

Page Range: Unknown

Description:

Field-Programmable Gate Arrays (FPGAs) are increasingly shaping the future of network security, thanks to their flexibility, parallel processing capabilities, and energy efficiency. In this survey, we examine 50 peer-reviewed studies published between 2020 and 2025, selected from an initial pool of 210 articles based on relevance, hardware implementation, and the presence of empirical performance data. These studies encompass a broad range of topics, including cryptographic acceleration, intrusion detection and prevention systems (IDS/IPS), hardware firewalls, and emerging strategies that incorporate artificial intelligence (AI) and post-quantum cryptography (PQC). Our review focuses on five major application areas: cryptographic acceleration, intrusion detection and prevention systems (IDS/IPS), hardware firewalls, and emerging strategies involving artificial intelligence (AI) and post-quantum cryptography (PQC). We propose a structured taxonomy that organises the field by technical domain and challenge, and compare solutions in terms of scalability, resource usage, and real-world performance. Beyond summarising current advances, we explore ongoing limitations—such as hardware constraints, integration complexity, and the lack of standard benchmarking. We also outline future research directions, including low-power cryptographic designs, FPGA–AI collaboration for detecting zero-day attacks, and efficient PQC implementations. This survey aims to offer both a clear overview of recent progress and a valuable roadmap for researchers and engineers working toward secure, high-performance FPGA-based systems.

Open Access: Yes

DOI: 10.3390/electronics14193894

SHEAB: A Novel Automated Benchmarking Framework for Edge AI

Sándor Répás Mustafa Abdulkadhim

Publication Name: Technologies

Publication Date: 2025-11-01

Volume: 13

Issue: 11

Page Range: Unknown

Description:

Edge computing is characterized by heterogeneous hardware, distributed deployment, and a need for on-site processing, which makes performance benchmarking challenging. This paper presents SHEAB (Scalable Heterogeneous Edge Automation Benchmarking), a novel framework designed to securely automate the benchmarking of Edge AI devices at scale. The proposed framework enables concurrent performance evaluation of multiple edge nodes, drastically reducing the time-to-deploy (TTD) for benchmarking tasks compared to traditional sequential methods. SHEAB’s architecture leverages containerized microservices for orchestration and result aggregation, integrated with multi-layer security (firewalls, VPN tunneling, and SSH) to ensure safe operation in untrusted network environments. We provide a detailed system design and workflow, including algorithmic pseudocode for the SHEAB process. A comprehensive comparative review of related work highlights how SHEAB advances the state-of-the-art in edge benchmarking through its combination of secure automation and scalability. We detail a real-world implementation on eleven heterogeneous edge devices, using a centralized 48-core server to coordinate benchmarks. Statistical analysis of the experimental results demonstrates a 43.74% reduction in total benchmarking time and a 1.78× speedup in benchmarking throughput using SHEAB, relative to conventional one-by-one benchmarking. We also present mathematical formulations for performance gain and discuss the implications of our results. The framework’s effectiveness is validated through the concurrent execution of standard benchmarking workloads on distributed edge nodes, with results stored in a central database for analysis. SHEAB thus represents a significant step toward efficient and reproducible Edge AI performance evaluation. Future work will extend the framework to broader workloads and further improve parallel efficiency.

Open Access: Yes

DOI: 10.3390/technologies13110515

Feature-Optimized Machine Learning Approaches for Enhanced DDoS Attack Detection and Mitigation

Sándor Répás Ahmed Jamal Ibrahim Nurullah Bektaş

Publication Name: Computers

Publication Date: 2025-11-01

Volume: 14

Issue: 11

Page Range: Unknown

Description:

Distributed denial of service (DDoS) attacks pose a serious risk to the operational stability of a network for companies, often leading to service disruptions and financial damage and a loss of trust and credibility. The increasing sophistication and scale of these threats highlight the pressing need for advanced mitigation strategies. Despite the numerous existing studies on DDoS detection, many rely on large, redundant feature sets and lack validation for real-time applicability, leading to high computational complexity and limited generalization across diverse network conditions. This study addresses this gap by proposing a feature-optimized and computationally efficient ML framework for DDoS detection and mitigation using benchmark dataset. The proposed approach serves as a foundational step toward developing a low complexity model suitable for future real-time and hardware-based implementation. The dataset was systematically preprocessed to identify critical parameters, such as packet length Min, Total Backward Packets, Avg Fwd Segment Size, and others. Several ML algorithms, involving Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Cat-Boost, are applied to develop models for detecting and mitigating abnormal network traffic. The developed ML model demonstrates high performance, achieving 99.78% accuracy with Decision Tree and 99.85% with Random Forest, representing improvements of 1.53% and 0.74% compared to previous work, respectively. In addition, the Decision Tree algorithm achieved 99.85% accuracy for mitigation. with an inference time as low as 0.004 s, proving its suitability for identifying DDoS attacks in real time. Overall, this research presents an effective approach for DDoS detection, emphasizing the integration of ML models into existing security systems to enhance real-time threat mitigation.

Open Access: Yes

DOI: 10.3390/computers14110472

Design of an Energy-Efficient SHA-3 Accelerator on Artix-7 FPGA for Secure Network Applications

Sándor Répás Abdulmunem A. Abdulsamad

Publication Name: Computers

Publication Date: 2026-01-01

Volume: 15

Issue: 1

Page Range: Unknown

Description:

As the demand for secure communication and data integrity in embedded and networked systems continues to grow, there is an increasing need for cryptographic solutions that provide robust security while efficiently using energy and hardware resources. Although software-based implementations of SHA-3 provide design flexibility, they often struggle to meet the performance and power limitations of constrained environments. This study introduces a hardware-accelerated SHA-3 solution tailored for the Xilinx Artix-7 FPGA. The architecture includes a fully pipelined Keccak-f [1600] core and incorporates design strategies such as selective loop unrolling, clock gating, and pipeline balancing to enhance overall efficiency. Developed in VHDL and synthesised using Vivado 2024.2.2, the design achieves a throughput of 1.35 Gbps at 210 MHz, with a power consumption of 0.94 W—yielding an energy efficiency of 1.44 Gbps/W. Validation using NIST SHA-3 vectors confirms its reliable performance, making it a promising candidate for secure embedded systems, including IoT platforms, edge devices, and real-time authentication applications.

Open Access: Yes

DOI: 10.3390/computers15010003

An AI-Driven Framework for Network Intrusion Detection Using ANOVA-Based Feature Selection

Sándor Répás Salam Allawi Hussein

Publication Name: International Journal of Advanced Computer Science and Applications

Publication Date: 2025-12-31

Volume: 16

Issue: 12

Page Range: 853-861

Description:

In the last few years, cyberattacks have become more complex, and it is becoming increasingly necessary to establish secure networks. This study examines enhancements to intrusion detection systems (IDSs) with the implementation of machine learning for the categorization of network traffic attacks. For the current study, we utilize four publicly available datasets: CICIDS2017, CIC-DoS2017, CSE-CIC-IDS2018, and CIC-DDoS2019. We examined three machine learning techniques: LightGBM, Random Forest, and XGBoost. Experimental results showed that RandomForest and XGBoost achieved the highest accuracy of 0.99 in both binary and multi-class intrusion detection tasks, maintaining balanced performance with macro F1-scores around 0.86. LightGBM exhibited slightly lower overall performance, but benefited from ANOVA-based feature selection, which improved its recall and model stability. Feature selection also enhanced computational efficiency by reducing feature redundancy while preserving accuracy across models. These results highlight how AI tools could help network security deal with emerging threats and improve the performance of IDS. The study underscores the critical role of feature selection in enhancing model efficiency, hence promoting advancements in automated network security systems that can adapt to evolving cyber threats.

Open Access: Yes

DOI: 10.14569/IJACSA.2025.0161280

A Hybrid Intrusion Detection Framework Using Deep Autoencoder and Machine Learning Models

Sándor Répás Salam Allawi Hussein

Publication Name: AI Switzerland

Publication Date: 2026-02-01

Volume: 7

Issue: 2

Page Range: Unknown

Description:

This study provides a detailed comparative analysis of a three-hybrid intrusion detection method aimed at strengthening network security through precise and adaptive threat identification. The proposed framework integrates an Autoencoder-Gaussian Mixture Model (AE-GMM) with two supervised learning techniques, XGBoost and Logistic Regression, combining deep feature extraction with interpretability and stable generalization. Although the downstream classifiers are trained in a supervised manner, the hybrid intrusion detection nature of the framework is preserved through unsupervised representation learning and probabilistic modeling in the AE-GMM stage. Two benchmark datasets were used for evaluation: NSL-KDD, representing traditional network behavior, and UNSW-NB15, reflecting modern and diverse traffic patterns. A consistent preprocessing pipeline was applied, including normalization, feature selection, and dimensionality reduction, to ensure fair comparison and efficient training. The experimental findings show that hybridizing deep learning with gradient-boosted and linear classifiers markedly enhances detection performance and resilience. The AE–GMM-XGBoost model achieved superior outcomes, reaching an F1-score above 0.94 ± 0.0021 and an AUC greater than 0.97 on both datasets, demonstrating high accuracy in distinguishing legitimate and malicious traffic. AE-GMM-Logistic Regression also achieved strong and balanced performance, recording an F1-score exceeding 0.91 ± 0.0020 with stable generalization across test conditions. Conversely, the standalone AE-GMM effectively captured deep latent patterns but exhibited lower recall, indicating limited sensitivity to subtle or emerging attacks. These results collectively confirm that integrating autoencoder-based representation learning with advanced supervised models significantly improves intrusion detection in complex network settings. The proposed framework therefore provides a solid and extensible basis for future research in explainable and federated intrusion detection, supporting the development of adaptive and proactive cybersecurity defenses.

Open Access: Yes

DOI: 10.3390/ai7020039

Introducing LEAF: LLM Edge Assessment Framework for Generative AI on the Edge

Sándor Répás Mustafa Abdulkadhim

Publication Name: Machine Learning and Knowledge Extraction

Publication Date: 2026-02-01

Volume: 8

Issue: 2

Page Range: Unknown

Description:

The transition of Large Language Models (LLMs) from centralized clouds to edge environments is critical for addressing privacy concerns, latency bottlenecks, and operational costs. However, existing edge benchmarking frameworks remain tailored to discriminative Deep Learning tasks (e.g., object detection), failing to capture the multidimensional challenges of generative AI, specifically the trade-offs between token generation speed, semantic accuracy, and hardware sustainability. To address this gap, we introduce LEAF (LLM Edge Assessment Framework), a novel evaluation methodology that integrates Circular Economy principles directly into performance metrics. LEAF assesses edge deployments across five synergistic pillars: Circular Economy Score, Energy Efficiency (Joules/Token), Performance Speed (Tokens/Second), semantic accuracy (BERTScore), and End-to-End Latency. We validate LEAF through an extensive experimental analysis of five distinct hardware classes, ranging from embedded IoT devices (Raspberry Pi 4 and 5, NVIDIA Jetson Nano) to professional edge servers (NVIDIA T400) and repurposed legacy workstations (NVIDIA GTX 1050 Ti). Utilizing 4-bit quantized models via the Ollama runtime, our results reveal a counterintuitive insight: repurposed consumer hardware significantly outperforms modern purpose-built edge SoCs. The legacy GTX 1050 Ti achieved a 20× speedup over the Raspberry Pi 4 and maintained superior energy-per-task efficiency compared to low-power ARM architectures by minimizing active runtime. These findings challenge the prevailing narrative that newer silicon is essential for Edge AI, demonstrating that sustainable, high-performance inference can be achieved by extending the lifecycle of existing hardware. LEAF thus provides a blueprint for a “Green Edge” ecosystem that balances computational capability with environmental responsibility.

Open Access: Yes

DOI: 10.3390/make8020048

FNR-IDS: A Fuzzy-Neural Hybrid with Real-Time RSA Encryption for Intelligent Intrusion Detection

Sándor Répás Ahmed Jamal Ibrahim

Publication Name: International Conference on Electrical Computer and Energy Technologies Icecet 2025

Publication Date: 2025-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The rising sophistication of Cybersecurity threats demands advanced Intrusion Detection Systems (IDS) capable of identifying abnormal network traffic with both accuracy and speed. This Research proposed FNR-IDS, a hybrid detection model that integrates Fuzzy Logic, Deep Neural Networks (DNNs), and RSA encryption to enhance both intrusion detection and data confidentiality. Using the UNSW-NB15 dataset, we apply Random Forest-based feature selection to extract key traffic attributes. A fuzzy inference engine evaluates the threat level and triggers RSA encryption for high-risk instances, while the DNN classifier ensures accurate detection. The integration of interpretability, learning capability, and real-time encryption addresses critical gaps in conventional IDS models. Experimental results show that FNR-IDS achieves 87% accuracy with an F1-score of 90% at the optimal threshold, confirming its effectiveness in detecting and mitigating modern cyberattacks. The proposed model of this article offers a robust, explainable, and secure framework for next-generation intrusion detection.

Open Access: Yes

DOI: 10.1109/ICECET63943.2025.11472342

Edge AI Benchmarking: Tools, Methodologies, and Optimization Strategies, a review

Sándor Répás Mustafa Abdulkadhim

Publication Name: International Conference on Electrical Computer and Energy Technologies Icecet 2025

Publication Date: 2025-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Edge computing has emerged as an important paradigm to address the evolving demands of latency-sensitive applications and the adaptation of Internet of Things (IoT) devices, offering near edge data processing to increase performance, reduce bandwidth usage, and increase data privacy. However, benchmarking these heterogeneous edge environments remains a challenge due to their distributed nature and diverse hardware configurations. This paper proposes "Scalable Heterogeneous Edge Automation Benchmarking"(SHEAB), a novel containerized and automated framework designed to evaluate edge computing systems comprehensively. SHEAB integrates containerization for portability, automation for efficiency, and a multi-layered security architecture - including firewalls, VPNs, and secure shell connections - to ensure robust data integrity across varied edge servers. This research advances the field by providing a scalable, secure, and adaptable benchmarking solution, with future directions aimed at researching hardware capability assessments and increasing AI-driven edge-computing testing and benchmarking.

Open Access: Yes

DOI: 10.1109/ICECET63943.2025.11472323