Browsing by Author "Dimitrova, Vesna"

Now showing 1 - 3 of 3

Advancing Image Spam Detection: Evaluating Machine Learning Models Through Comparative Analysis
(MDPI, 2025) Jamil, Mahnoor; Trpcheska, Hristina Mihajloska; Popovska-Mitrovikj, Aleksandra; Dimitrova, Vesna; Creutzburg, Reiner
Image-based spam poses a significant challenge for traditional text-based filters, as malicious content is often embedded within images to bypass keyword detection techniques. This study investigates and compares the performance of six machine learning models-ResNet50, XGBoost, Logistic Regression, LightGBM, Support Vector Machine (SVM), and VGG16-using a curated dataset containing 678 legitimate (ham) and 520 spam images. The novelty of this research lies in its comprehensive side-by-side evaluation of diverse models on the same dataset, using standardized dataset preprocessing, balanced data splits, and validation techniques. Model performance was assessed using evaluation metrics such as accuracy, receiver operating characteristic (ROC) curve, precision, recall, and area under the curve (AUC). The results indicate that ResNet50 achieved the highest classification performance, followed closely by XGBoost and Logistic Regression. This work provides practical insights into the strengths and limitations of traditional, ensemble-based, and deep learning models for image-based spam detection. The findings can support the development of more effective and generalizable spam filtering solutions in multimedia-rich communication platforms.
Citation - WoS: 0
Citation - Scopus: 0
Mathematical Foundations and Implementation of Coniks Key Transparency
(Mdpi, 2024) Dağ, Hasan; Dag, Hasan; Dimitrova, Vesna; Management Information Systems
This research paper explores the CONIKS key management system's security and efficiency, a system designed to ensure transparency and privacy in cryptographic operations. We conducted a comprehensive analysis of the underlying mathematical principles, focusing on cryptographic hash functions and digital signature schemes, and their implementation in the CONIKS model. Through the use of Merkle trees, we verified the integrity of the system, while zero-knowledge proofs were utilized to ensure the confidentiality of key bindings. We conducted experimental evaluations to measure the performance of cryptographic operations like key generation, signing, and verification with varying key sizes and compared the results against theoretical expectations. Our findings demonstrate that the system performs as predicted by cryptographic theory, with only minor deviations in computational time complexities. The analysis also reveals significant trade-offs between security and efficiency, particularly when larger key sizes are used. These results confirm that the CONIKS system offers a robust framework for secure and efficient key management, highlighting its potential for real-world applications in secure communication systems.
Citation - WoS: 0
Citation - Scopus: 0
Securing Ai Systems: a Comprehensive Overview of Cryptographic Techniques for Enhanced Confidentiality and Integrity
(Ieee, 2024) Garcia, Jose Luis Cano; Dağ, Hasan; Udechukwu, Izuchukwu Patrick; Ibrahim, Isiaq Bolaji; Chukwu, Ikechukwu John; Dag, Hasan; Dimitrova, Vesna; Mollakuqe, Elissa; Management Information Systems
The rapid evolution of artificial intelligence (AI) has introduced transformative changes across industries, accompanied by escalating security concerns. This paper contributes to the imperative need for robust security measures in AI systems based on the application of cryptographic techniques. This research analyzes AI-ML systems vulnerabilities and associated risks and identifies existing cryptographic methods that could constitute security measures to mitigate such risks. Information assets subject to cyberattacks are identified, such as training data and model parameters, followed by a description of existing encryption algorithms and a suggested approach to use a suitable technique, such as homomorphic encryption CKKS, along with digital signatures based on ECDSA to protect the digital assets through all the AI system life cycle. These methods aim to safeguard sensitive data, algorithms, and AI-generated content from unauthorized access and tampering. The outcome offers potential and practical solutions against privacy breaches, adversarial attacks, and misuse of AI-generated content. Ultimately, this work aspires to bolster public trust in AI technologies, fostering innovation in a secure and reliable AI-driven landscape.