International Journal of Information and Computer Security (11 papers in press)

Regular Issues

• Automatic fake news detection using an optimised transformer with deer hunting optimisation algorithm  
  by Yamini Devi Jonnala, J. Sirisha Devi 
  Abstract: Fake news has become a significant issue, influencing public opinion and decision-making across various platforms. Traditional machine learning algorithms often struggle to accurately detect subtle contextual details within misleading information. Transformer-based models, with their self-attention mechanisms, are particularly well-suited for this task, as they capture deeper contextual relationships within the text. This study proposes an advanced fake news detection system utilising a transformer encoder model, focusing on textual analysis for precise classification. By leveraging the transformers ability to identify complex patterns and contextual nuances, the system improves the detection of misleading or false information. To further enhance model performance, hyperparameter optimisation is applied using the deer hunting optimisation algorithm (DHOA). The system is evaluated on a benchmark dataset, demonstrating its effectiveness with high recall and precision metrics. The proposed approach addresses the escalating issue of misinformation by combining cutting-edge natural language processing with an innovative optimisation technique. For the proposed method, transformer encoders were used, achieving an accuracy of 98.71%, a recall of 98.7%, and an F-measure of 98.8% on dataset 1. on dataset 2, the model achieved an accuracy of 98.23%, a recall of 98.24%, and an F-measure of 98.36%.
  Keywords: transformer encoders; deer hunting optimisation algorithm; DHOA; fake news; hyperparameter.
  DOI: 10.1504/IJICS.2026.10079776
   
  
• W-state and chaotic mapping-driven: a new three-party key agreement protocol  
  by Ningning Xu, Haocheng Kan, Peng Guo, Hongfeng Zhu 
  Abstract: In three-party communication scenarios, the high cost of quantum devices poses a significant barrier to the widespread adoption of quantum key agreement technologies. To address this challenge, we propose a novel semi-quantum key agreement (SQKA) protocol. This protocol integrates W-states and chaotic sequences to simultaneously prevent information leakage and malicious tampering during communication. The core innovations of the proposed scheme are threefold: first, the pseudo-randomness of chaotic sequences is introduced into quantum communication, which ensures the security of classical channel transmission while generating non-unique sequences for enhanced flexibility; second, the strong entanglement property of W-states is leveraged to enable timely detection of channel attacks; third, a two-way verification mechanism between communicating parties is incorporated to further strengthen interaction security. The security assessment indicates that this protocol can resist both internal and external attacks. Finally, compared with the communication efficiency of other schemes, our scheme can still maintain a very high efficiency of 8.7%.
  Keywords: semi-quantum; W-state; chaotic sequence; key agreement.
  DOI: 10.1504/IJICS.2026.10079777
   
  
• DEARNN: a hybrid deep learning approach for cyberbullying detection in Twitter social media platform  
  by Nagaraju Sonti, T.V.L. Pranathi, S. Alekhya, T. Haritha, M.L. Illisha 
  Abstract: Cyberbullying is becoming a more widespread problem on social media, especially on sites like Twitter where identification is made more difficult by colloquial language and concealed connotations. In order to detect dangerous texts, this study presents dual encoder attention-based recurrent neural network (DEARNN), a sophisticated deep learning model. DEARNN uses an attention mechanism to highlight important passages in the text that are suggestive of bullying and uses recurrent neural networks (RNNs) to assess word sequences. Furthermore, word embeddings improve the models capacity to recognise intricate patterns. By identifying both overt and covert kinds of bullying, DEARNN outperforms conventional techniques, according to testing on huge Twitter datasets. In order to increase accuracy, future improvements will concentrate on adding multimedia material and broadening language support.
  Keywords: cyberbullying detection; recurrent neural networks; RNNs; deep learning; language model.
  DOI: 10.1504/IJICS.2026.10079806
   
  
• Context-aware differential privacy for federated learning in healthcare  
  by Kalyani Pampattiwar, Namrata Patel, Masooda Modak 
  Abstract: Rising interest in collaborative medical artificial intelligence has encouraged adoption of federated learning to protect patient data. Yet many models add uniform differential privacy noise, ignoring patient age, disease severity and institutional risk, which weakens the trade-off between privacy and model utility in heterogeneous healthcare data. We present a context-aware differential privacy framework for federated learning that provides patient-level, context-specific privacy through five modules: patient-aware noise calibration network assigns noise from demographics and disease factors disease-specific gradient clipping sets complexity-adjusted thresholds federated context embedding exchange shares non-identifiable context embeddings adaptive contextual utility estimator predicts local utility loss and adjusts noise hierarchical privacy budget scheduler allocates budgets across patients, hospitals and disease cohorts. On multi-institutional healthcare datasets, the framework improves privacy efficiency by 25%, retains over 95% baseline accuracy and increases robustness under non-independent and identically distributed conditions, enabling practical, privacy-adaptive federated systems for clinical decision support at scale.
  Keywords: federated learning; differential privacy; healthcare AI; patient-specific privacy; context-aware privacy; process.
  DOI: 10.1504/IJICS.2026.10079981
   
  
• Ensemble learning for anomaly detection: a comparative study of fusion of classical and neural models in cybersecurity logs  
  by Mrityunjay Brahma, Hemanta Kumar Kalita 
  Abstract: In the face of increasingly sophisticated cyber threats, traditional signature-based detection systems often fall short, especially against zero-day attacks. This research presents a hybrid anomaly detection framework that integrates classical supervised machine learning algorithms and deep learning models to enhance detection accuracy while minimising false positive rates. Using the UNSW NB15 proxy server dataset, we evaluate various classical machine learning models k-nearest neighbours, decision trees, Naive Bayes, logistic regression, random forest, and gradient boosting alongside neural networks like multi-layer perceptron and long short-term memory. Two ensemble based models (M1 with multilayer perceptron, M2 with long short-term memory) are designed using soft voting classifiers, combining algorithm subsets in odd-numbered groupings (3, 5, 7) to ensure clear majority decisions. Our findings demonstrate that the ensemble approach significantly improves classification performance, with model M1s largest ensemble (seven algorithms) achieving up to 99% accuracy and with lowest 1% false positive rate. This study underscores the effectiveness of combining machine learning and neural networks/deep learning methods for adaptive, scalable, and precise network anomaly detection systems, providing a robust defense against evolving cybersecurity threats.
  Keywords: classical supervised learning; cyber security; deep learing; ensemble model; neural network.
  DOI: 10.1504/IJICS.2026.10079982
   
  
• A fingerprint-based biometric cryptosystem for enhanced security and cryptographic key strength evaluation using statistical tests  
  by Reshma Nadaf, Satish S. Bhairannawar 
  Abstract: Confidential information transferred across unsecure channels can be securely protected cryptographic methods. In this paper, we propose a new encryption and decryption framework for the advanced encryption standards (AESs) algorithm, in which a users fingerprint serves as the cryptographic key for safe communication. Our method extracts biometric features from the users fingerprints using the minutiae extraction technique. By integrating encryption and extracted minutiae features into a probabilistic symmetric cryptosystem, our research suggests a way to minimise dependency on pseudo random number generators and reduce operational complexity. This research work proposes a novel key generation framework which uses key derivation function (KDF) with biometric features to generate a stable and unique 128-bit string used for encryption and decryption process. Statistical tests like frequency test, runs test, auto-correlation test and high density and low density tests are conducted to check randomness and unpredictability of cryptographic keys generated from fingerprint images.
  Keywords: biometrics; fingerprint; AES key generation; Biometric cryptosystem; statistical tests.
  DOI: 10.1504/IJICS.2026.10080165
   
  
• Graph anonymisation in online social networks using modified generative adversarial networks and variable Fossa optimisation algorithm  
  by Nithish Ranjan Gowda, Venkatesh, V.R. Venugopal 
  Abstract: In this paper, we propose a dual-method framework for OSN anonymisation that considers both privacy preservation and utility retention over graph data. In the first method, the deep learning model modified generative adversarial network (M-GAN) is used to successively acquire the privacy and utility objectives and build anonymised graphs. In that M-GAN based graph anonymisation framework, the discriminator network is enhanced with an improved graph isomorphism network (I-GIN) integrated with the iPool algorithm, which retains the most informative features in arbitrary graphs. The second approach employs a variable Fossa optimisation algorithm (VFOSA), which significantly reduces structural information loss (SIL) during the clustering phase of the structural k-anonymity model, resulting in a highly efficient anonymised network. In VFOSA, the original Fossa optimisation algorithm is improved through a dynamic step-size mechanism. The performance of the proposed scheme is evaluated in terms of subgraph classification accuracy and node classification accuracy.
  Keywords: online social networks; OSNs; graph anonymisation; privacy preservation; modified GAN; improved graph isomorphism network; I-GIN; variable Fossa optimisation algorithm; VFOSA.
  DOI: 10.1504/IJICS.2026.10080166
   
  
• Cyber-savvy or cyber-sloppy? Exploring Indian e-banking users security behaviour  
  by S. Prasanna, V. Mariappan, S. P. Nisha Pradeepa, R. Mani, S. Saravanan 
  Abstract: As the banking sector adopts technology as a key driver of success, cybersecurity has become a pivotal defence against growing cyber threats. Recognising the importance of user behaviour alongside technological issues, this study examines e-banking users cybersecurity behaviour through relevant psychological constructs, using the knowledge-attitude-behaviour model as the primary framework. A new conceptual framework based on cognitive load theory, andragogy, and the knowledge-attitude-behaviour model is developed and empirically tested using data from 772 Indian e-banking users. Structural equation modelling is used to analyse the proposed relationships. The findings reveal that bank efforts and customer initiatives shape users CSK. In addition, attitude, memory recall, and CSK positively influence cybersecurity behaviour, while technophilia emerges as a complex moderating factor. Overall, the results underscore the influence of cognitive, attitudinal, and learning-related factors on cybersecurity practices and provide insights into CSK acquisition and behavioural formation.
  Keywords: cybersecurity behaviour; CSB; information security; cybersecurity knowledge; CSK; memory recall; technophilia; customer efforts; CE; e-banking.
  DOI: 10.1504/IJICS.2026.10080408
   
  
• Efficient and secure heterogeneous signcryption for multi-message and multi-receiver communications in VANETs  
  by Mahesh Palakollu, Gowri Thumbur, P. Vasudeva Reddy 
  Abstract: Vehicular ad hoc networks (VANETs) enable direct communication among vehicles and roadside units to enhance traffic safety and management. However, the broadcast nature of wireless communication and the used of diverse cryptographic frameworks create serious security and interoperability challenges. To address these issues, this paper presents a pairing-free certificateless heterogeneous signcryption scheme supporting multi-messages and multi-receiver communication for VANETs. This scheme allows a sender in a certificateless cryptographic environment to securely transmit multiple messages to multiple receivers operating under public key infrastructure, without certificate management overhead or key escrow issues. Security is formally analysed in the ROM model under the hardness of the ECDLP. Performance analysis show that the scheme significantly improves the efficiency ranging from 49.23% to 96.65% over existing approaches. It also ensures confidentiality, authenticity, privacy preservation, and forward secrecy, making it suitable for resource-constrained VANET applications.
  Keywords: heterogeneous signcryption; certificateless framework; pairing free; ECDLP; confidentiality and authentication; vehicular ad hoc networks; VANETs.
  DOI: 10.1504/IJICS.2026.10080475
   
  
• Shamirs sharing-based encryption: recursive sharing propagation for scalable and resilient symmetric encryption  
  by Ilhem Djeziri, Kamel Mohamed Faraoun 
  Abstract: This paper presents a recursive symmetric encryption framework based on Shamir-inspired polynomial transformations and evolving hidden states over GF(2128). Unlike CBC and CTR modes, which require one pseudorandom permutation (PRP) call per plaintext block, the proposed scheme propagates cryptographic randomness through recursive finite-field operations, reducing PRP usage. A hidden recursive state is initialised using a secure PRP, then plaintext blocks are recursively embedded into finite-field polynomials whose evaluations partially form the ciphertext while remaining shares are internally reused. This process produces algebraic diffusion and sequential ciphertext dependency. A formal analysis proves IND-CPA security under standard PRP assumptions and shows that the hidden states remain computationally indistinguishable from random values. Vandermonde-matrix optimisations enable scalable implementation with low overhead. Experimental results from a Rust implementation show improved performance over CBC and CTR while preserving strong avalanche and diffusion properties.
  Keywords: Shamir’s secret sharing; provable symmetric encryption; scalable encryption; quantum-upgradeable security.
  DOI: 10.1504/IJICS.2026.10081084
   
  
• Secure colour image encryption using improved ECC with KOAWOA algorithm and OTP generation  
  by Nilesh N. Thorat, Amit Singla, Tanaji Anandrao Dhaigude, Sumit Arun Hirve 
  Abstract: This research proposes a novel hybrid cryptographic framework that integrates improved elliptic curve cryptography (ImECC) with modified HMAC-based one-time password (MHOTP) generation, optimised through the newly introduced kookaburra merged walrus optimisation (KOAWOA) algorithm. The proposed method consists of two primary phases: embedding (encryption) and extraction (decryption). During the encryption process, three original images and two secret images undergo multi-layered encryption using random grid-based secret image sharing, extended visual cryptography scheme (EVCS), and kronecker product-based encryption, ensuring a highly secure and robust encryption mechanism. The KOAWOA algorithm is introduced as an advanced hybrid optimisation technique to generate optimal encryption keys, significantly enhancing security and reducing computational overhead. KOAWOA employs an adaptive metaheuristic strategy to improve randomness, making it highly resistant to attacks. Additionally, in the ImECC-based encryption stage, the MHOTP generation technique is utilised, where dynamically generated OTPs serve as encryption keys.
  Keywords: kookaburra merged walrus optimisation algorithm; improved elliptic curve cryptography; ImECC; visual cryptography; Baker’s map; MHOTP generation.
  DOI: 10.1504/IJICS.2026.10081171