International Journal of Computer Science and Technology

International Journal of Computer Science and Technology | Vol. 3, No. 10, October 2022 | pp. 1–8

DOI: 10.46882/2022/IJCST/000213

Article Type: Original Research Paper

Title: Quantifying Adversarial Vulnerabilities in Graph Neural Networks via Targeted Topology Perturbation

Names of Authors: Wei-Dong Zhang¹, Amara Okafor²

Authors’ Affiliations: ¹School of Computer Science, Yangtze University of Technology, Wuhan, China; ²Department of Systems Engineering, University of Nigeria, Nsukka, Nigeria

Abstract: Graph Neural Networks (GNNs) are widely used to analyze relational structured applications like financial fraud detection maps and biological interactions. However, their structural dependency makes them highly vulnerable to malicious structural manipulations. This paper introduces an adversarial testing mechanism designed to evaluate GNN resilience by introducing targeted perturbations to node connections. The algorithm calculates node-centrality values alongside structural gradients to find and modify high-impact link structures with minimal modifications. We tested this attack method on standard benchmark network configurations, focusing primarily on GCN and GraphSAGE architectures. The assessment reveals that modifying a tiny fraction (less than 2.5%) of network links degrades node-classification accuracy by 38.4%. This drop demonstrates that minor topology edits can severely bypass standard neural classification security steps. To mitigate this vulnerability, we outline a robust structural defense strategy rooted in localized neighborhood-degree validation. This defense effectively neutralizes up to 72.0% of adversarial edge modifications during training operations.

Keywords: Graph Neural Networks, Adversarial Attacks, Topology Perturbation, Node Classification, Network Robustness, Machine Learning

Manuscript Timeline: Received: May 20, 2022; Revised: June 28, 2022; Accepted: July 22, 2022; Published: October 08, 2022

International Journal of Computer Science and Technology | Vol. 3, No. 9, September 2022 | pp. 1–8

DOI: 10.46882/2022/IJCST/000212

Article Type: Original Research Paper

Title: Minimizing Query Delays in Geographically Replicated NoSQL Systems via Dynamic Consensus Scaling

Names of Authors: Elena Rostova¹, Jean-Luc Picard²

Authors’ Affiliations: ¹Data Engineering Laboratory, NordTech University, Oslo, Norway; ²Distributed Systems Architecture Division, SynthData Systems, Paris, France

Abstract: Maintaining strict transactional consistency across globally distributed database systems typically leads to high query latency and performance bottlenecks. This research proposes an optimized database replication framework that uses an adaptive variant of the Raft consensus algorithm. The algorithm dynamically measures regional round-trip network performance and modifies quorum execution targets based on localized traffic requirements. When operational volatility is minimal, the system relaxes global synchronization states down to localized clusters. It returns to full multi-region confirmation phases exclusively during high write-concurrency periods. We deployed the framework across a distributed cloud testbed containing 12 distinct geographic nodes to evaluate performance. The experimental findings indicate a 42.1% reduction in mean write latency compared to standard, non-adaptive Raft configurations. The transactional throughout achieved a sustainable capacity of 18,500 operations per second under complex read-to-write workloads. This dynamic adjustment methodology minimizes global operational staleness without compromising overall transactional durability metrics.

Keywords: NoSQL Databases, Raft Consensus, Data Replication, Query Latency, Distributed Systems, Transactional Consistency

Manuscript Timeline: Received: May 15, 2022; Revised: June 24, 2022; Accepted: July 19, 2022; Published: September 05, 2022

International Journal of Computer Science and Technology | Vol. 3, No. 8, August 2022 | pp. 57–64

DOI: 10.46882/2022/IJCST/000211

Article Type: Original Research Paper

Title: Real-Time Edge Analytics for Automated Fault Detection in Industrial Cyber-Physical Systems

Names of Authors: Siddharth Mehta¹, Hiroshi Tanaka²

Authors’ Affiliations: ¹Department of Automation and Robotics, Tech-Vanguard Institute, Mumbai, India; ²Industrial IoT Solutions Group, Nippon Automation Corp, Yokohama, Japan

Abstract: High-speed assembly operations within modern manufacturing frameworks require instant anomaly recognition to protect equipment and avoid operational pauses. Traditional architectures transmit raw sensory feeds directly into central databases, inducing substantial network latency delays. This article introduces an adaptive edge-computing framework optimized to run real-time anomaly assessments directly at the device layer. The system relies on a structural One-Class Support Vector Machine (1-SVM) engine designed to flag voltage, thermal, and vibration anomalies. The algorithm monitors machine telemetry patterns continuously and estimates deviation vectors over a moving observation frame. We validated this decentralized architecture on a live multi-axis CNC testbed containing 45 high-frequency sensors. Empirical results prove the system identifies early degradation indicators within a strict latency threshold of ±12 ms. Operating at the device layer reduced the baseline outbound telemetry bandwidth consumption by 74.5%. This shift effectively minimizes cloud storage overhead requirements while preserving edge-layer processing accuracy. A standard t-test confirmed the consistency of the classification precision across multi-day manufacturing runs (p < 0.01).

Keywords: Cyber-Physical Systems, Edge Computing, Fault Detection, Industrial Automation, One-Class SVM, Real-Time Analytics

Manuscript Timeline: Received: May 11, 2022; Revised: June 20, 2022; Accepted: July 15, 2022; Published: August 04, 2022

International Journal of Computer Science and Technology | Vol. 3, No. 7, July 2022 | pp. 49–56

Research Article

Title: A Decentralized Federated Learning Architecture with Non-IID Data Mitigation for Distributed Edge Computing

Names of Authors: Chao Zhang¹, Xianfeng Wang², and Jun Lin³

Authors’ Affiliations:
¹School of Computer Science, Wuhan University, Wuhan, China
²Department of Electronic Information, Huazhong University of Science and Technology, Wuhan, China
³State Key Laboratory of Software Development Environment, Beihang University, Beijing, China

Abstract: Abstract: Centralized federated learning architectures rely heavily on a single orchestrating server to aggregate local gradients, introducing structural single points of failure and significant wide-area network bottlenecks. Furthermore, data collected across heterogeneous edge devices is often non-independently and identically distributed (non-IID), which compromises global model accuracy and decelerates algorithm convergence. This paper introduces an optimized, completely decentralized peer-to-peer federated learning framework designed for edge computing environments without central server dependencies. Individual edge nodes train deep neural network parameters locally on native datasets and exchange model weights exclusively with single-hop topological neighbors using an asynchronous gossip consensus protocol. To counter client-side data divergence, a localized dynamic regularization factor is integrated into the native objective function, punishing severe weight drift away from neighboring consensus baselines. Communication overhead is minimized through an adaptive gradient quantization routine that compresses transmission payload sizes dynamically based on instantaneous wireless link states. Matrix simulations using skewed MNIST and CIFAR-10 data distributions demonstrate that the proposed decentralized protocol achieves a high classification accuracy of 92.4%, matching centralized baseline performance while lowering total wide-area network data transmission volume by 46.2%. The framework provides stable, private machine learning capabilities for high-mobility mobile ad-hoc environments.

Keywords: Federated learning, Edge computing, Gossip protocol, Non-IID data, Gradient compression, Decentralized optimization

Manuscript Timeline: Received: April 14, 2022; Revised: May 20, 2022; Accepted: June 15, 2022; Published: July 1, 2022

Citation: Zhang, C., Wang, X., & Lin, J. (2022). A decentralized federated learning architecture with non-IID data mitigation for distributed edge computing. International Journal of Computer Science and Technology, 3(7), 49–56. DOI: 10.46882/2022/IJCST/000031

International Journal of Computer Science and Technology | Vol. 3, No. 6, June 2022 | pp. 41–48

Research Article

Title: A Hybrid Generative Adversarial Network for High-Fidelity Image Super-Resolution in Digital Pathology

Names of Authors: Jean Dupont¹, Marie Laurent², and Pierre Mercier³

Authors’ Affiliations:
¹Laboratory of Computer Science and Systems, Aix-Marseille University, Marseille, France
²Department of Information Technology, Télécom Paris, Palaiseau, France
³Institute of Digital Health, University of Montpellier, Montpellier, France

Abstract: High-resolution digital pathology scans are crucial for accurate tumor grading, tissue structure evaluation, and cellular anomaly identification. However, clinical scanning hardware is limited by optical constraints and high processing costs, often yielding histopathological images with lower pixel resolution that can obscure critical diagnostic markers. This paper presents a hybrid Generative Adversarial Network (GAN) architecture specifically optimized for high-fidelity image super-resolution in digital pathology workflows. The proposed framework enhances standard patch-based architectures by integrating a residual-in-residual dense network (RRDN) back-bone to improve texture feature generation. To prevent checkerboard artifacts and structural blurring, a composite loss function—incorporating pixel-wise mean squared error, perceptual VGG feature distance, and a specialized structural similarity index (SSIM) penalty—guides model training. Validation experiments on open pathology tissue datasets demonstrate that the hybrid network increases image dimensions four-fold while maintaining a Peak Signal-to-Noise Ratio (PSNR) of 31.4 decibels (dB) and an SSIM score of 0.895. Blind evaluations by clinical pathologists confirm that the super-resolved images successfully preserve structural cell boundaries and nuclear chromatin distributions, outperforming standard bicubic interpolation and standard residual network models.

Keywords: Digital pathology, Image super-resolution, Generative adversarial networks, Deep learning, Histopathology, Structural similarity index

Manuscript Timeline: Received: March 18, 2022; Revised: April 25, 2022; Accepted: May 18, 2022; Published: June 1, 2022

Citation: Dupont, J., Laurent, M., & Mercier, P. (2022). A hybrid generative adversarial network for high-fidelity image super-resolution in digital pathology. International Journal of Computer Science and Technology, 3(6), 41–48. DOI: 10.46882/2022/IJCST/000030

International Journal of Computer Science and Technology | Vol. 3, No. 5, May 2022 | pp. 33–40

Research Article

Title: A Secure and Privacy-Preserving Data Aggregation Scheme for Smart Grid Advanced Metering Infrastructures

Names of Authors: Ali Al-Zaabi¹, Fatma Al-Hassan², and Mona Al-Mansoori³

Authors’ Affiliations:
¹Department of Electrical and Computer Engineering, United Arab Emirates University, Al Ain, UAE
²Department of Computer Science, Khalifa University, Abu Dhabi, UAE
³College of Technological Innovation, Zayed University, Dubai, UAE

Abstract: Advanced Metering Infrastructure (AMI) networks in modern smart grids enable utilities to collect high-frequency electrical consumption statistics from residential smart meters to balance grid loads and optimize power generation distribution. However, transmitting fine-grained power metrics over open networks creates data privacy risks, as third-party analysis could reveal private household habits and daily occupancy routines. This paper proposes a secure, privacy-preserving data aggregation scheme tailored for smart grid AMI communication loops. The proposed protocol implements homomorphic encryption based on the Paillier cryptosystem, allowing intermediate local data aggregators to sum electrical readings algebraically without decrypting individual customer metrics. To counter internal security threats and fake measurement injections, an elliptic curve digital signature scheme provides end-to-end source validation. Security analysis demonstrates that the aggregation protocol resists eavesdropping, data alteration, and collusion attacks, even if regional data concentrators become compromised. Computational profiling confirms that smart meter encryption processing requires 1.8 ms, and regional verification cycles complete efficiently, verifying its viability for high-density smart electrical distribution networks.

Keywords: Smart grid privacy, Advanced metering infrastructure, Homomorphic encryption, Data aggregation, Cyber-physical security, Paillier cryptosystem

Manuscript Timeline: Received: February 16, 2022; Revised: March 24, 2022; Accepted: April 20, 2022; Published: May 1, 2022

Citation: Al-Zaabi, A., Al-Hassan, F., & Al-Mansoori, M. (2022). A secure and privacy-preserving data aggregation scheme for smart grid advanced metering infrastructures. International Journal of Computer Science and Technology, 3(5), 33–40. DOI: 10.46882/2022/IJCST/000029