International Journal of Information and Computer Security (9 papers in press)

Regular Issues

• Hybrid energy and opcode sequence-based detection of automation attacks in online social networks using SSFCM classification  
  by Anjali Rawat, Anand Rajavat 
  Abstract: Online social network automation attacks (OSNAA) increasingly employ automated tools to perform malicious activities such as bot-based interactions, email hijacking, and malware-driven manipulation. This study introduces an automated social network attack detection model (ASNADM) that integrates energy consumption footprint analysis (EComp-FP) with automated software opcode sequence analysis (ASOSA-OSM) to identify automation-based anomalies at the client side. The framework analyses behavioral energy traces from CPU and system activity alongside opcode n-gram representations derived from executable binaries using opcode frequency variance (OFV) and weighted term frequency (TF-W). These heterogeneous features are fused and classified using self-adaptive soft fuzzy C-means (SSFCM) clustering. Experiments conducted on the SPEMC-15K-E dataset demonstrate a detection accuracy of 99.93% with a 0.07% false-positive rate, outperforming DT, KNN, RF, and SVM models. Results confirm that abnormal energy patterns and low-entropy opcode sequences effectively reveal malicious automation in online social networks.
  Keywords: online social network automation attacks; OSNAA; energy consumption footprint analysis; EComp-FP; opcode sequence mining; self-adaptive soft fuzzy C-means; SSFCM; client-side anomaly detection.
  DOI: 10.1504/IJICS.2026.10077393
   
  
• Detecting and countering battery-depletion attacks in wearable medical devices  
  by Shakir A. Mehdiyev 
  Abstract: Although large-scale cyberattacks on wearable medical devices (WMDs) are not yet widespread, the growing complexity and connectivity of these systems make them a potential target for battery-draining threats. Devices such as pacemakers, insulin pumps, and neurostimulators are critically dependent on a stable power supply to perform life-sustaining functions. This article explores the possible causes of increased energy consumption, including cyber impacts on sensor, computational, and communication modules. In response to these challenges, the paper proposes an approach that combines adaptive power management with a lightweight intrusion detection system tailored to the specific characteristics of WMDs. The study emphasises the importance of implementing energy-efficient and proactive strategies to enhance the resilience of these devices against emerging cyber-physical threats.
  Keywords: wearable medical devices; WMDs; sensors; energy vulnerabilities; battery failures; cyberattacks; energy monitoring.
  DOI: 10.1504/IJICS.2026.10077999
   
  
• Context-aware sensitive information detection in unstructured text using BERT  
  by Longjam Velentina Devi, Navanath Saharia 
  Abstract: This paper proposes a BERT-based token classification model specifically designed for detecting sensitive information inside unstructured text data. Unlike existing sentence level or context level classification methods, our methodology allows for finer granularity by examining individual words as well as their impact on one another. Previously available methods often misclassify non-sensitive information such as customer care or toll-free numbers as sensitive data, but our methodology effectively distinguish between genuinely sensitive information and non-sensitive public contact numbers, improving precision and reducing false positives. Our model surpasses previous techniques on key criteria, with an accuracy of 98%, precision of 0.98 and F1-score of 0.99 performing better than the existing model by a considerable margin. This study highlights the effectiveness of classification for sensitive data detection and establishes a new benchmark for token-level analysis contributing to more secure and effective sensitive content management.
  Keywords: bidirectional encoder representations from transformers; BERT; privacy; machine learning; security; privacy; deep learning; CRF; sensitive information; personally identifiable information; PII.
  DOI: 10.1504/IJICS.2026.10078195
   
  
• Fake profile detection on social media using hybrid 2D CNN and AES-BiLSTM with network analysis  
  by Sujit Kumar Badodia, Hemant Makwana 
  Abstract: Detecting and eliminating fake profiles is crucial to maintaining the integrity of social media platforms and ensuring user safety. This paper proposed a hybrid artificial intelligence model to address these challenges by combining advanced preprocessing, feature extraction and classification techniques. For feature extraction, principal component analysis (PCA) is used to decrease the dimensionality of the data, ensuring efficient processing. The hybrid classification framework integrates a 2D convolutional neural network (2D CNN) to extract spatial features from the input data. Additionally, an attention-enhanced stacked BiLSTM (AES-BiLSTM) is utilised to capture temporal features, while the added attention mechanisms improve the models focus on the most relevant information. The 2D CNN and AES-BiLSTM models are further enhanced through hybrid optimisation, with their hyperparameters fine-tuned using the seagull optimisation algorithm (SOA). This approach achieves a high accuracy of 98.9%, precision of 98.9%, specificity of 98.9%, and an F1-score of 99%.
  Keywords: principal component analysis; PCA; 2D convolutional neural network; 2D CNN; AES-BiLSTM; fake profile detection; seagull optimisation algorithm; SOA.
  DOI: 10.1504/IJICS.2026.10078196
   
  
• Enhancing rare attack detection in network intrusion systems through data augmentation  
  by Ahmad Farid Aseel, Amir Hosein Keyhanipour 
  Abstract: Cyberattacks are becoming increasingly sophisticated, making it challenging for network intrusion detection systems (NIDS) to detect rare attacks due to severe class imbalance in network traffic data. This study evaluates LightGBM, XGBoost, and random forest models combined with data balancing techniques (ADASYN, SMOTE, and random oversampling) using the UNSW-NB15 and CICIDS2017 datasets. Results demonstrate that oversampling methods enhance minority class detection, with ADASYN achieving the highest performance - improving recall for Worms from 0.528 to 1.000 and F1-score for Shellcode from 0.834 to 1.000. On CICIDS2017, the model reached 99.96% accuracy, even for rare attacks like Heartbleed. Key innovations include clustering-based data reduction, outlier removal via IQR, and comparative analysis of augmentation methods. The study confirms ADASYNs effectiveness in addressing imbalance and boosting NIDS sensitivity, offering a practical solution for real-world cybersecurity applications.
  Keywords: intrusion detection; machine learning; data balancing; ADASYN.
  DOI: 10.1504/IJICS.2026.10078615
   
  
• Cross-year cyber-attack detection and temporal generalisation: an explainable machine learning approach  
  by Archana R. Laddhad, Gurveen Vaseer 
  Abstract: The rapid evolution of cyber threats presents significant challenges for intrusion detection systems (IDS), particularly when it comes to adapting to new and unseen attack patterns. This study investigates the effectiveness of cross-year cyber-attack classification, with a focus on explainable machine learning (ML) to diagnose and understand the evolving nature of cyber threats. Specifically, we leverage decision trees as an interpretable model to identify critical features that contribute to the classification of network traffic, allowing for a transparent understanding of the decision-making process. By analysing and comparing the attack patterns across two years, we explore the changes in feature importance and the shifting characteristics of emerging threats. The findings highlight the challenges posed by evolving attacks and demonstrate how explainable ML methods can enhance the interpretability of IDS models, improving their ability to adapt to new threats. This work contributes valuable insights into the dynamic nature of cyber threats and emphasises the need for IDS systems that are both adaptive and transparent in their operation.
  Keywords: cybersecurity; intrusion detection systems; IDS; explainable machine learning; decision trees; cross-year analysis.
  DOI: 10.1504/IJICS.2026.10078770
   
  
• Hybrid optimised deep learning model for detecting malicious nodes in mobile network  
  by Gotte Ranjith Kumar, K. Suresh Babu 
  Abstract: Malicious nodes pose growing threats to mobile networks by disrupting communication and reducing performance, while existing detection methods often suffer from high overhead and poor scalability. To address this, this study proposes a chronological addax optimisation algorithm based siamese convolutional neural network (CrAOA-SCNN), CrAOA combined with a Siamese CNN for malicious node detection. The proposed framework begins with a mobile network simulation, where routing is managed using the ad hoc on-demand distance vector (AODV) protocol and node trustworthiness is estimated through a trust evaluation mechanism. The SCNN model identifies malicious nodes, while its hyperparameters are optimised using CrAOA. The proposed routing strategy results in a delay of 0.247 sec, a data packet delivery ratio of 92.89%, and a trust of 88.89%, as well as the superior accuracy, true negative rate (TNR), and true positive rate (TPR) of 91.37%, 90.84%, and 90.49% are achieved in malicious node detection.
  Keywords: mobile network; ad hoc on-demand distance vector; AODV; malicious node; Siamese convolutional neural network; addax optimisation algorithm; AOA.
  DOI: 10.1504/IJICS.2026.10078813
   
  
• Blockchain-based public examination management platform  
  by Dhruti Sharma, Kuldeep Kevat, Dhvani Maktuporia, Meet Oza, Dev Sadisatsowala 
  Abstract: The public examinations can be considered as a critical pathway for academic admission, employment selection, skill certification, etc. Such examinations are typically conducted by public examination management (PEM) platforms. Though the current PEM in India offers operational efficiency, they are still vulnerable to various malpractices including leakage of question paper, unauthorised access of confidential information, candidate impersonation as well as insider threat. Over the past decade, several hardware, software, and cryptography-based solutions have been proposed for secure exam conduction; however, none of them address all key vulnerabilities within a unified framework. In response, we propose a blockchain-based PEM (BPEM) platform integrating the cryptographic techniques, blockchain technology, and decentralised storage, i.e., interplanetary file system (IPFS). The proposed platform ensures tamper proof question paper collection and distribution, secure registration and authentication of candidates, and immutable result declaration effectively promoting fairness, trust, and accountability in public examination systems.
  Keywords: blockchain; smart contracts; interplanetary file system; IPFS; public examination management; cryptography; biometric authentication; question paper leakage; candidate impersonation.
  DOI: 10.1504/IJICS.2026.10078845
   
  
• A comparative performance analysis of automated cloud security remediation architectures for AWS cloud environments  
  by Vitalii Molnar, Dmytro Sabodashko, Ivan Opirskyy 
  Abstract: This research evaluates the performance of three remediation strategies for addressing critical cloudsecurity misconfigurations: manual intervention, pollingbased automation, and eventdriven automation. Experiments were conducted within a single AWS account and region under controlled load, simulating two highimpact yet relatively simple scenarios: publicdata exposure through storagepolicy modification and unrestricted remote access due to securitygroup misconfiguration. Each approach was assessed using key metrics time to detect (TTD), time to remediate (TTR), and total automated response time (T_ART) across repeated trials to ensure statistical validity, assuming remediation functions remained in a warm state. Within this constrained experimental setting, eventdriven remediation achieved the lowest response times, consistently below ten seconds, whereas pollingbased and manual methods exhibited substantially higher latency. These findings suggest that, for similar classes of misconfigurations and deployment conditions, eventdriven workflows can provide faster and more consistent remediation, potentially reducing the dwell time of misconfigurations, although generalisation to multiregion and largescale environments requires further investigation.
  Keywords: cloud security; cloud misconfiguration; automated remediation; event-driven architecture; AWS Config; Amazon EventBridge; response latency; security automation; performance benchmarking.
  DOI: 10.1504/IJICS.2026.10078942