Computer Engineering Commons^™

Hybrid Deep (Cnn-Bilstm) Intrusion Detection For Defense And Mission-Critical Networks, Corey A Cheng, Jermaine Anim-Addo, Asma Jakir Hussain, Zion O Smith-Fox, Sanjay Goel, Yuksel Celik

Military Cyber Affairs

This article examines how hybrid deep learning can strengthen intrusion detection for military and defense networks. Using the CSE-CIC-IDS2018 dataset, the study evaluates a CNN-BiLSTM model designed to detect benign traffic and multiple attack categories, including DDoS, DoS, botnet, brute-force, web attack, and infiltration activity. The model achieved strong multi-class detection performance, with 0.9893 accuracy and 0.9979 ROC-AUC. The findings suggest that AI-supported intrusion detection can improve cyber defense operations, analyst triage, and protection of mission-critical networks.

Are Large Language Models Safe? A Vulnerability Analysis Of Generated Source Code, James Richards-Perhatch, Mitchell Milander, James M. Halvorsen, Assefaw Gebremedhin

Military Cyber Affairs

The increasing complexity of software and demands for rapid deployment have pushed the software industry to rely more on large language models (LLMs) in developing source code. However, as this technology is still relatively recent, questions can arise about the safety of the generated code. This paper presents an analysis of seven LLMs with respect to the presence of vulnerabilities within source code. Our findings show that LLMs are more likely to produce vulnerable web applications than vulnerable C programs, and that vulnerabilities are more likely to occur when program size and complexity increases.

Semantic Shields: Automating Critical Infrastructure Defense Via Nlp-Driven Ransomware Profiling, Henry Trowbridge, Ian Zalcberg, Ryan Schley, Carter Yagemann, Natasha Phan, Srikar Maduposu, Vimal Buck

Military Cyber Affairs

Ransomware poses a growing threat to critical infrastructure, where successful attacks can disrupt operational technology (OT) and industrial control systems (ICS) with significant public safety consequences. However, attributing ransomware incidents to specific threat actors remains challenging due to ransomware-as-a-service ecosystems, actor rebranding, and the obfuscation of traditional indicators of compromise. This paper presents Semantic Shields, an NLP-driven attribution framework that leverages BERT-generated semantic embeddings and DBSCAN clustering to profile ransomware actors through the linguistic characteristics of ransom notes. Using a dataset of 295 ransom notes from 189 distinct threat groups, the framework achieved an 87.2% true positive clustering rate and …

Llm-Generated Countermeasures For Iot Cyberattacks, James Alger, Michael Tu

Military Cyber Affairs

The rapid expansion of the Internet of Things (IoT) has introduced significant cybersecurity challenges, particularly for resource-constrained devices that traditional intrusion detection systems often fail to protect effectively. This paper proposes a novel, two-phase autonomous security pipeline designed to bridge the gap between probabilistic threat detection and deterministic network enforcement. The framework first utilizes a custom Time Series Transformer (TST) to classify multivariate network traffic and identify specific attack vectors, such as ransomware, SQL injections, and malicious file uploads. In the second phase, an agentic AI layer, comprising a locally hosted Large Language Model (LLM) orchestrated via LangGraph, processes the …

Foreward, Todd Arnold

Military Cyber Affairs

No abstract provided.

Letter From The Director: Mastery In Practice, Joseph Schafer

Military Cyber Affairs

No abstract provided.

Challenges, Trends, And The Role Of Lstm In Ai-Based Predictive Maintenance Of Electrolyzers For Solar Hydrogen Systems: A Review, Yani Koerniawan Kuatno, Muhamad Zahim Sujod

Turkish Journal of Electrical Engineering and Computer Sciences

The transition toward low-carbon energy systems has increased interest in hydrogen as a clean energy carrier, with solar-driven water electrolysis emerging as a promising technology due to its high efficiency and compatibility with renewable energy sources. However, dynamic operating conditions and intermittent renewable input accelerate electrolyzer degradation, reducing reliability and system lifespan. Predictive maintenance (PdM), supported by artificial intelligence (AI), offers a data-driven approach to anticipate failures and improve operational durability. This review systematically investigates AI-based PdM approaches for electrolyzers, with an emphasis on long short-term memory (LSTM) networks and Internet of things (IoT) integration. Following PRISMA 2020 guidelines, 35 …

Dynamic Focal Loss Adjustment For Railway Defect Detection, Mehmet Koç, Ridvan Özdemi̇r, Ömer Gerek

Turkish Journal of Electrical Engineering and Computer Sciences

Railway infrastructure is critical to the safe and efficient operation of transportation systems, and the early detection of defects is essential for preventing catastrophic failures. Automated defect detection methods are therefore crucial for maintaining continuous safety while reducing maintenance costs. Although Focal Loss is widely used in object detection under class-imbalanced conditions, its fixed α parameter may limit its effectiveness in detecting rare defects. In this study, we propose an adaptive α-tuned Focal Loss approach that dynamically adjusts class weights based on average precision (AP) values. By iteratively optimizing α without relying on gradient-based optimization, the proposed method improves the …

Relative Rate Observer-Based Online Tuning Mechanism For Single-Input Interval Type-2 Fuzzy Pid Controllers, Oqba Aldreiei, Cenk Ulu, Mert Can Kurucu, Müjde Güzelkaya

Turkish Journal of Electrical Engineering and Computer Sciences

The characteristics of the footprint of uncertainty (FOU) in interval type-2 membership functions (IT2-MFs) are crucial to the performance and robustness of interval type-2 fuzzy controllers (IT2-FCs). However, existing IT2-FC design approaches mostly use fixed FOU structures. This study proposes an online membership function (MF) adjustment mechanism for a single-input interval type-2 fuzzy PID controller (SIT2-FPID)  that adjusts the FOU of the antecedent MFs and weights of the consequent MFs, respectively, to achieve high performance and robustness. The proposed online adjustment mechanism consists of a relative rate observer (RRO), a two-input rule-base adjustment system, and a first-order smoothing filter. The …

Cuip-X25: A Real-World Network Intrusion Dataset For Next-Generation Ai-Driven Security, Arshad Iqbal, Sohail Asghar

Turkish Journal of Electrical Engineering and Computer Sciences

The efficacy of artificial intelligence (AI) in intrusion detection systems (IDS) is critically dependent on high-fidelity training data. However, as detailed in the manuscript's literature review, existing benchmark datasets are predominantly synthetic, outdated, or imbalanced and fail to capture the complexity of the contemporary threat landscape. To bridge this gap, this study introduces CUIP-X25, a novel real-world cyber-attack dataset captured over a four-month period using a dionaea honeypot deployed on a public network. Unlike synthetic alternatives, this dataset provides an authentic representation of modern adversarial tactics, techniques, and procedures, encompassing 3.16 million real events across ten distinct attack categories, including …

Robust Load Frequency Control For Multiarea Electrical Power Systems Via Analytical Proportional-Integral-Derivative Plus Second Order Derivative Controller Design, Yavuz Güler, Mustafa Nalbantoğlu, Ibrahim Kaya

Turkish Journal of Electrical Engineering and Computer Sciences

This research presents a proportional-integral-derivative plus second order derivative (PIDD2) controller design based on the Direct Synthesis Method (DSM) for load frequency control (LFC) of interconnected power systems. The parameters of the proposed PIDD2 controller are determined using the DSM, which offers an analytical approach for tuning. The design approaches have been developed specifically for single, two, and three-area power systems, encompassing nonreheated and reheated thermal turbines. In the proposed design method, the best values of PIDD2 controller parameters were found by using a multicriteria objective function that includes the integral of absolute error (IAE) and settling time. In response …

Boundary Layer Sliding Mode Control Strategy For Variable-Speed Compressor In Deep Freezers: Experimental Validation Of Energy Efficiency And Freezing Capacity, Sertan Aksoy, Kami̇l Çeti̇n, Sezai̇ Taşkin

Turkish Journal of Electrical Engineering and Computer Sciences

This study presents the design and experimental validation of a nonlinear sliding mode controller developed for a deep freezer equipped with a variable-speed compressor. The proposed control strategy aims to minimize energy consumption while maintaining rapid and stable cooling performance under varying ambient conditions. A detailed thermal model of the deep freezer was established using an equivalent resistance–capacitance network representation, enabling precise analysis of temperature dynamics. The sliding mode-based control algorithm dynamically adjusts the compressor’s operating frequency according to temperature deviation, ambient conditions, and time-dependent factors, providing robust performance without requiring parameter retuning for different models. Beyond theoretical-based analysis, a …

Empowering Edge Intelligence Through Reparameterized Lightweight Transformers And Distributed Inference, Hosein Esmaeili, Mohammad Ali Afshar Kazemi, Reza Radfar, Nazanin Pilevari

Turkish Journal of Electrical Engineering and Computer Sciences

Deploying advanced transformer-based models on resource-constrained edge devices remains a significant challenge due to their high memory footprint and substantial compute requirements. In this paper, we propose a reparameterized transformer framework that integrates High-Rank Factorization (HRF) during training, layer merging at inference, and dynamic, load-balanced distributed inference across multiple devices. To further reduce resource usage, our framework supports mixed-precision quantization down to 4-bit, enabling flexible accuracy–latency–energy trade-offs. Experimental evaluations on the ESC-50 environmental sound dataset demonstrate that our method matches or exceeds the performance of larger baseline models while using 20–30% fewer parameters, achieving up to 48% latency reduction in …

Measurement-Aware Zero-Phase Iterative Learning Control For Robust Regulation Of Nonideal Boost Converters In Electric Vehicle Fast Charging, Aytaç Altan, Mohammed S. Alzaidi, Cağfer Yanarateş

Turkish Journal of Electrical Engineering and Computer Sciences

Integrating battery energy storage with DC-DC boost converters for electric vehicle fast charging exposes the regulator to ageing-induced parameter drift, periodic load pulses, and, critically, the nonidealities in the output-voltage sensing chain. This paper proposes a measurement-aware, zero-phase iterative learning control scheme for robust output-voltage regulation of a nonideal boost converter whose parameters are matched to those of a commercial Texas Instruments TPS6102x battery regulator. The controller combines an inner proportional-integral stabilizing loop with an outer zero-phase learning law that updates a feedforward correction based on the sensor-captured output trajectory; a forward-backward robustness filter suppresses the amplification of measurement noise …

A Binary Multiobjective Hippopotamus Optimization Algorithm For Feature Selection In Phishing Website Detection, Fatima Belmessaoud, Sofiane Maza, Djaafar Zouache

Turkish Journal of Electrical Engineering and Computer Sciences

Phishing website detection remains a major challenge in cybersecurity as attackers continuously develop new techniques to deceive users. Identifying the most informative features from large datasets is essential to improve classification accuracy while reducing computational complexity. Feature selection is therefore widely addressed using metaheuristic optimization techniques due to their flexibility and global search capability. In this study, we propose a Binary Multiobjective Hippopotamus Optimization Algorithm (B-MOHOA) for feature selection in phishing website detection. The proposed method simultaneously optimizes two conflicting objectives: maximizing classification accuracy and minimizing the number of selected features. Unlike many existing studies that mainly focus on transfer …

Range–Angle-Dependent Oam Beamforming With A Concentric Helical Circular Fda, Uğur Yeşi̇lyurt

Turkish Journal of Electrical Engineering and Computer Sciences

Secure and spatially selective wireless transmission requires orbital angular momentum (OAM) beams that are confined to a specific range and angle, rather than propagating indefinitely along the beam axis. In this paper, a concentric helical circular frequency diverse array (CHCFDA) is proposed to generate range–angle-dependent OAM beams without requiring external phase shifters. The helical element positioning inherently provides the necessary interelement phase distribution through physical step height, while logarithmically increasing frequency offsets are applied across concentric rings—and optionally across individual elements—to eliminate range periodicity and achieve a single, well-focused OAM beam exclusively at the target location. Both linear and logarithmic …

Between Blockchain And Black Markets: South Africa's Legal Readiness For Crypto-Driven Cyberfraud, Sagwadi Mabunda, Yassin Chande

Communications of the IIMA

This paper examines whether the proliferation of cryptocurrency-facilitated fraud warrants a reclassification of the terrestrial crime of fraud into the distinct statutory offence of cyberfraud under South African law. Engaging with established fraud typologies — exit scams, Initial Coin Offering (ICO) scams, Ponzi schemes, pump-and-dump schemes, and market manipulation — the article tests their definitional fit against both the common law of fraud and section 8 of the Cybercrimes Act 19 of 2020. Through a hypothetical composite scenario combining multiple fraud typologies, the article demonstrates that whilst cryptocurrency significantly amplifies the reach and complexity of fraudulent schemes, it functions primarily …

Saas As The Backbone Of Digital Transformation: How Ai Turned Cloud Software Into Intelligent Enterprise Infrastructure, Amar Fejzić

Communications of the IIMA

Software-as-a-Service (SaaS) has become one of the most consequential infrastructures of digital transformation because it lowers the cost, time, and complexity of adopting enterprise capabilities. At the same time, artificial intelligence (AI), especially generative and conversational AI, is changing SaaS from a delivery model into an intelligent operating layer that automates workflows, personalizes customer interactions, and supports data-driven decisions. This paper develops a conceptual synthesis of academic literature and public organizational cases to examine how SaaS shaped digital transformation and how AI is reshaping SaaS itself. The analysis shows that SaaS enables scalable experimentation, faster deployment, and modular integration, while …

Doing Less With More: A First-Principles Exploration Of The Suitability Of Agentic Computing Over Alternative Architectural Choices, Ritvik Garimella, Biplav Srivastava, Amit Sheth

Publications

There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter's seeming ease of use. Never has it been easier, or costlier, to do less with more. However, little is known about when agents are preferable to established alternatives such as local computation, Representational State Transfer (REST), the Simple Object Access Protocol (SOAP), and the Model Context Protocol (MCP), particularly when development speed, performance, and operational cost are considered. We investigate this question using a controlled mathematical task that compares seven methods on a benchmark of 1,000 arithmetic expressions where semantics of operator precedence has …

Designing Classifact: Towards A Transparent And Secure Platform For Stakeholder-In-The-Loop Data Annotation, Philippine Waisvisz

Communications of the IIMA

AI systems depend on human judgment, yet many annotation workflows are either designed for data-science specialists or managed through external commercial platforms. The first approach may demand more technical skills than relevant stakeholders possess. The second can require organizations to transfer data, expertise, and governance to an outside provider. Both can limit the involvement of people who understand what data means in its real-world context. Human-in-the-loop approaches introduce human judgment. Stakeholder-in-the-loop annotation focuses on selecting and organizing people whose contextual knowledge fits the AI application.

This paper presents Classifact, a transparent and secure platform for stakeholder-in-the-loop data annotation and validation. …