Aleksandar Miljković
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Aleksandar Miljković has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Milan Čabarkapa
Faculty of Engineering, University of Kragujevac, 34000 Kragujevac, Serbia
3 shared publications - Aleksa Maksimović1 shared publication
- Aleksandar Đorđević
University of Nis
1 shared publication - Darko Stefanovic
Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia
1 shared publication - Dragan Ranđelović
Faculty of Diplomacy and Security, University Union-Nikola Tesla, 11000 Belgrade, Serbia
1 shared publication - Filip Miljković1 shared publication
Latest Publications
- Open Access
- 19 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4297
White-Box and Transfer-Based Black-Box Adversarial Attacks on Neural Network Models for Credit Card Fraud Detection
Machine learning models deployed for credit card fraud detection operate in adversarial, security-critical settings, and their robustness against evasion attacks directly affects financial and operational risk. However, despite extensive work on models for credit card fraud detection, comparatively fewer studies have examined their adversarial vulnerability. This study proposes a targeted Projected Gradient Descent-based attack on feedforward neural network models for credit card fraud detection. The attack is evaluated in white-box and black-box settings, illustrating the extent to which adversarial vectors generated on a surrogate attack model may be transferred to a set of victim models. The experimental settings are designed to ensure a fair, mixed-feature attack, including introduction of perturbation bound constraints, preservation of the class imbalance, specification of attack success criteria, selection of victim models, and avoiding bias. The obtained adversarial transaction vectors are evaluated in terms of their effect on model predictions and their mathematical proximity to the corresponding original fraudulent vectors. Finally, the evaluation results and limitations of the scope of the study are discussed.
- 19 September 2026
- Published by MDPI AG in Electronics
- Vol. 15 (18) , 4297
Open AccessWhite-Box and Transfer-Based Black-Box Adversarial Attacks on Neural Network Models for Credit Card Fraud Detection
Machine learning models deployed for credit card fraud detection operate in adversarial, security-critical settings, and their robustness against evasion attacks directly affects financial and operational risk. However, despite extensive work on models for credit card fraud detection, comparatively fewer studies have examined their adversarial vulnerability. This study proposes a targeted Projected Gradient Descent-based attack on feedforward neural network models for credit card fraud detection. The attack is evaluated in white-box and black-box settings, illustrating the extent to which adversarial vectors generated on a surrogate attack model may be transferred to a set of victim models. The experimental settings are designed to ensure a fair, mixed-feature attack, including introduction of perturbation bound constraints, preservation of the class imbalance, specification of attack success criteria, selection of victim models, and avoiding bias. The obtained adversarial transaction vectors are evaluated in terms of their effect on model predictions and their mathematical proximity to the corresponding original fraudulent vectors. Finally, the evaluation results and limitations of the scope of the study are discussed.
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Computer and Forensic Sciences
- Vol. 2 (1) , 43-52
A system architecture for preventing social engineering attacks via e-mail
Modern business and the expansion of internet technology have caused a great growth in communication via electronic mail. Bearing in mind that the weakest link in any system is the human, the greatest danger of unauthorized access to ICT resources is recognized in this section of the system [6]. For this reason, the greatest attention regarding the protection of ICT systems should be focused on the users and preventive response to phishing campaigns as the most common form of cyber attack. This paper will present the system architecture for preventive response to phishing campaigns. The architecture itself, which will be explained in the continuation of the text, consists of several different modules integrated into a whole. First, a sender analysis module, which would be based on the blacklist principle; next, an email attachment analysis module, which would perform the functions of static and dynamic analysis of potentially malicious attachments; a link analysis module, which would include the application of Cortex, an open source intelligence service; and finally, a text analysis module, based on statistical models.
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Computer and Forensic Sciences
- Vol. 2 (1) , 43-52
A system architecture for preventing social engineering attacks via e-mail
Modern business and the expansion of internet technology have caused a great growth in communication via electronic mail. Bearing in mind that the weakest link in any system is the human, the greatest danger of unauthorized access to ICT resources is recognized in this section of the system [6]. For this reason, the greatest attention regarding the protection of ICT systems should be focused on the users and preventive response to phishing campaigns as the most common form of cyber attack. This paper will present the system architecture for preventive response to phishing campaigns. The architecture itself, which will be explained in the continuation of the text, consists of several different modules integrated into a whole. First, a sender analysis module, which would be based on the blacklist principle; next, an email attachment analysis module, which would perform the functions of static and dynamic analysis of potentially malicious attachments; a link analysis module, which would include the application of Cortex, an open source intelligence service; and finally, a text analysis module, based on statistical models.
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Computer and Forensic Sciences
- Vol. 2 (1) , 29-41
iTrust News Certificate: A blockchain-based solution for news verification and reputation management
The proliferation of fake news and misinformation in the digital era poses a significant challenge to news organizations and content creators. In this paper, we introduce the iTrust News Certificate, the architecture of an online blockchain-based solution designed to combat fake news, enhance news verification, and maintain reputation within the media ecosystem. Unlike previous attempts, iTrust News Certificate focuses on user-friendly features while ensuring transparency and reliability. By leveraging blockchain technology, iTrust News Certificate establishes a decentralized and immutable ledger for storing news-related metadata. This ledger ensures the integrity and traceability of news articles, making it extremely difficult for malicious actors to tamper with or propagate false information.
- 1 January 2023
- Published by Centre for Evaluation in Education and Science (CEON/CEES) in Journal of Computer and Forensic Sciences
- Vol. 2 (1) , 29-41
iTrust News Certificate: A blockchain-based solution for news verification and reputation management
The proliferation of fake news and misinformation in the digital era poses a significant challenge to news organizations and content creators. In this paper, we introduce the iTrust News Certificate, the architecture of an online blockchain-based solution designed to combat fake news, enhance news verification, and maintain reputation within the media ecosystem. Unlike previous attempts, iTrust News Certificate focuses on user-friendly features while ensuring transparency and reliability. By leveraging blockchain technology, iTrust News Certificate establishes a decentralized and immutable ledger for storing news-related metadata. This ledger ensures the integrity and traceability of news articles, making it extremely difficult for malicious actors to tamper with or propagate false information.
- Open Access
Triple Modular Redundancy Optimization for Threshold Determination in Intrusion Detection Systems
This paper presents a novel approach for an Intrusion Detection System (IDS) based on one kind of asymmetric optimization which use any three already well-known IDS algorithms and Triple Modular Redundancy (TMR) algorithm together. Namely, a variable threshold which indicates an attack on an observed and protected network is determined by using all three values obtained with three known IDS algorithms i.e., on previously recorded data by making a decision by majority. For these algorithms authors used algorithm of k-nearest neighbors, cumulative sum algorithm, and algorithm of exponentially weighted moving average. Using a proposed method we can get a threshold that is more precisely determined than in the case of any method individual. Practically, using TMR we obtain a dynamically threshold adjustment of IDS software, which reduces the existence of false alarms and undetected attacks, so the efficiency of such IDS software is notably higher and can get better results. Today, Denial of Service attacks (DoS) are one of the most present type of attacks and the reason for the special attention paid to them in this paper. In addition, the authors of the proposed method for IDS software used a known CIC-DDoS2019 dataset, which contains various data recordings of such attacks. Obtained results with the proposed solution showed better characteristics than each individual used algorithm in this solution. IDS software with the proposed method worked precisely and timely, which means alarms were triggered properly and efficiently.
Open AccessTriple Modular Redundancy Optimization for Threshold Determination in Intrusion Detection Systems
This paper presents a novel approach for an Intrusion Detection System (IDS) based on one kind of asymmetric optimization which use any three already well-known IDS algorithms and Triple Modular Redundancy (TMR) algorithm together. Namely, a variable threshold which indicates an attack on an observed and protected network is determined by using all three values obtained with three known IDS algorithms i.e., on previously recorded data by making a decision by majority. For these algorithms authors used algorithm of k-nearest neighbors, cumulative sum algorithm, and algorithm of exponentially weighted moving average. Using a proposed method we can get a threshold that is more precisely determined than in the case of any method individual. Practically, using TMR we obtain a dynamically threshold adjustment of IDS software, which reduces the existence of false alarms and undetected attacks, so the efficiency of such IDS software is notably higher and can get better results. Today, Denial of Service attacks (DoS) are one of the most present type of attacks and the reason for the special attention paid to them in this paper. In addition, the authors of the proposed method for IDS software used a known CIC-DDoS2019 dataset, which contains various data recordings of such attacks. Obtained results with the proposed solution showed better characteristics than each individual used algorithm in this solution. IDS software with the proposed method worked precisely and timely, which means alarms were triggered properly and efficiently.