OPOlha Partyka

Olha Partyka

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Olha Partyka has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • CONTEXTUAL VALIDATION OF RISK-RELATED FEATURES IN FORENSIC ANALYSIS SYSTEMS USING ARTIFICIAL INTELLIGENCE

    by T. O. Fedynyshyn, O. O. Partyka

    Automated systems and language models in digital forensics select material from mobile-device exports for expert review. This paper adds contextual validation of an identified feature–artifact pair to this process. The method helps distinguish a person's account of their actions from a quotation. It examines the fragment alongside related messages and data, checks the person's role, the fragment's exact source location and provenance, and whether the feature warrants expert review. If the model cannot determine whether the material supports the feature, the result is recorded as undetermined. Otherwise, selection requires all checks to pass. Selected material includes a source reference. The experiment used 600 synthetic cases grouped into 300 pairs of comparable cases: similar fragments requiring different decisions because of context, attribution, or provenance. It covered 20 primary features and five context types. Against the expected decisions defined during dataset generation, full-context analysis incorrectly selected 155 of 300 cases lacking grounds for selection. Checks applied to the same responses reduced this count to 41. Among 300 supported cases, selection decreased from 297 to 289. Overall, 330 cases were selected, 241 rejected, and 29 recorded as undetermined. These results concern one local model and predefined metadata.

  • Open Access

    IDENTIFICATION AND AUTHENTICATION SYSTEMS IN THE CONTEXT OF MODERN INFORMATION SECURITY THREATS

    by Oleh Harasymchuk, Ivan Opirskyy, Dmytro Sabodashko, Ivan Kolbasynskyi, Petro Haraniuk, Khrystyna Ruda, Yevhenii Kurii, Vitalii Susukailo, Valerii Dudykevych, Andrii Partyka, et al.

    The monograph aims to provide a detailed analysis of current biometric authentication technologies using electrocardiographic (ECG) signals and voice as two fundamentally different but complementary modalities. The relevance of the work is due to the ongoing and evolving crisis of password-based security mechanisms (annual leaks affecting billions of user accounts, and generative speech synthesis technologies moving towards levels where the human voice can be imitated in a matter of minutes). The combination of ECG (an innate marker of life that is almost impossible to fake) with voice (which provides simple contactless verification at a distance) forms a logical and specialized premise for a new generation of biometric structures. The first part is devoted to the basic theory of biometric technologies: nine principles (uniqueness, stability, measurability, universality, resistance to counterfeiting, security, accuracy, standardization and acceptability) for building systems; a comparative analysis of nine physiological and behavioral modalities; nine functional modules of a typical biometric system; architectural solutions from autonomous to cloud-based and adaptive with Zero Trust support; a system of quality assessment metrics – FAR/FRR/EER/DET/minDCF curves – and approaches to ensuring demographic equity. The second part is devoted exclusively to ECG-based biometrics. The unique characteristics of the electrocardiographic signal, arising from anatomical, electrophysiological and neurohumoral factors, are further explained in physiological terms. All processing stages are described – from signal acquisition (with contact and non-contact methods), noise filtering (adaptive LMS filter or 1D U-Net based on neural networks), cardiac cycle segmentation using the Pan–Tompkins algorithm, autoencoder architectures, formation of morphological, temporal and spectral features for average heart beat analysis and dimensionality reduction based on PCA/LDA – up to classification and decision making. Comparison of two-class SVM, k-NN, decision trees and neural networks in different configurations was performed using four datasets (MIT-BIH, PTB, Fantasia, Lviv Biometric Data Set). The highest identification accuracy (98.90%, FAR 0.18·10⁻³, FRR 7.32·10⁻³) was achieved by a neural network with a hidden layer architecture (256, 128). It was experimented with deep embedding architectures (1D-ResNet, Transformer) as well as metric loss functions (Triplet Loss, ArcFace) and tested whether it is possible to deploy it on edge devices. The third section contains the full voice biometric chain: classical MFCC, LPC and PNCC descriptors, speech preprocessing methods (spectral subtraction, Wiener filtering, VAD and neural network optimization using Wave-U-Net), and finally four modern neural network architectures for speaker embedding-ECAPA-TDNN/WavLM/TitaNet/PyAnnote. In the framework of the experimental study, it is shown that TitaNet achieves the highest verification accuracy (0.96), and ECAPA-TDNN – 0.95 and scales better with increasing number of users; while WavLM, under difficult conditions, demonstrates the highest sensitivity to channel variations. The fourth section covers several practical implementation topics: international legal regulation (GDPR, AI Act, BIPA, ISO/IEC 24745 and 30107 standards), ethical aspects of the use of biometric data, architectural solutions for industrial implementation (design of a template database with approximate search algorithms: HNSW and IVF-PQ; cancelable biometric methods; fault tolerance; integration of BioAPI and FIDO2), implementation scenarios in the e-ID industry: banking, telecommunications, medicine, public administration and corporate security; the topic of the user interface - from ease of use to accessibility and economic analysis of costs against return on investment. Strategic development opportunities are identified: multimodal integration of ECG and voice at the level of feature fusion, scoring and decision-making; adaptive systems based on federated learning with differentiated privacy against threats from generative AI; transfer to decentralized identification based on Zero-Knowledge Proof. The scientific novelty of the work is determined by a new integrated concept of biometric authentication with a combination of ECG and voice; a comparative study of modern embedding architectures not only with an assessment of accuracy, but also with a determination of the scalability of models and resistance to spoofing attacks, based on the most modern generative models; as well as a quantitative measurement of how serious a threat these models pose to voice biometrics systems. The practical significance depends on the ability to directly apply the results to build biometric systems in finance, telecommunications, medicine and other areas of social activity. The monograph is designed for researchers, graduate students and students of specialties in information security, digital signal processing and machine learning, as well as for practicing specialists in the field of design and implementation of biometric authentication systems.

  • Open Access

    PROTECTION OF THE WIRELESS-NETWORK REPUTATION MECHANISM AGAINST ERRONEOUS UPDATES IN THE PRESENCE OF COMPROMISED NODES USING A TYPED k-OUT-OF-N RULE

    by Olha Partyka

    In wireless networks, node reputation is often updated by comparing a local report with the global fusion decision. Under incomplete coverage or in the presence of compromised sources, this decision may not provide a reliable reference, and a correct report from an honest node may therefore receive a negative update. This paper considers a typed representation of the k-out-of-N outcome intended to reduce such false penalties. The underlying binary decision remains unchanged, while the fusion outcome is additionally classified as a single quorum, double quorum, unreached quorum, insufficient coverage, or no-data state. Reputation is updated only in the single-quorum H1 or H0 states. Implementation correctness was verified by exhaustive enumeration of 15,309 configuration–quota pairs. Classical updating, coverage filtering, a two-sided quorum rule, Bayesian variants, and beta reputation with forgetting were compared experimentally. The base scenario used N=7, k=4, two compromised nodes, and a prior probability P(H1)=0.5. At an abstention probability of 0.5, classical updating produced about 34% unjust penalties of honest nodes, coverage filtering about 28%, whereas typed updating reduced this value to 1.9%. The mean trust difference between honest and compromised nodes was about 0.59. Ablation analysis showed that for k=4 the same result is reproduced by a simpler two-sided quorum rule, while for k=3 the full typology provides a small additional gain. The results indicate that accounting for the structure of the global decision can reduce false penalties of honest nodes without changing the underlying k-out-of-N rule. In practical use, this prevents an insufficiently supported global decision from being unconditionally used as a reference for reputation updates.

  • Open Access

    RISK-AWARE CYBERATTACK DETECTION IN WIRELESS NETWORKS CONSIDERING THE ROBUSTNESS OF MACHINE LEARNING MODELS

    by Olha Partyka

    Intrusion detectors for wireless networks are still commonly assessed on unchanged test sets. Such evaluation does not cover a deliberate modification of controllable traffic features or the use of model explanations to identify a vulnerable direction. A high test score therefore says little about detector behaviour under an active attack. This paper examines a risk-aware pipeline that combines a gradient-boosted base classifier, SHAP explanations, a logistic risk meta-classifier, and selective referral to a human analyst. Risk is described by three signals: the base attack probability, cosine stability of a local SHAP explanation relative to a class-specific training centroid, and Mahalanobis distance from the training distribution. This combination is intended to capture not only the predicted class, but also whether the reasoning pattern and the record itself are familiar to the model. A fixed five percent of records is referred for review according to explanation instability, predictive uncertainty, or predictive entropy. The experiments use a controlled synthetic dataset and NSL-KDD. Two attacks are evaluated: a one-step, gradient-free SHAP-sign perturbation and a transferred projected-gradient attack. The results are not uniform across datasets. On the synthetic benchmark, uncertainty and entropy provide the best selective results; under transferred PGD, macro-F1 on the retained 95 percent rises from 0.882 ± 0.008 for the base detector to 0.908 ± 0.008. NSL-KDD gives a different ordering. Explanation stability is more useful on clean and SHAP-sign-perturbed records, whereas under transferred PGD neither selective configuration improves on C3: macro-F1 is 0.699 for C3, 0.696 for C4, and 0.694 for C4-conf/ent. The base detector also deteriorates markedly, from 0.791 ± 0.003 on clean NSL-KDD to 0.579 ± 0.004 under SHAP-sign and 0.637 ± 0.002 under transferred PGD. These results do not support choosing a review rule from clean validation data alone. Selective referral can manage the accuracy–coverage trade-off, but it is not an adversarial defence. Before deployment, the pipeline should be tested on current Wi-Fi, IoT, 5G, and 6G traffic, with semantically valid perturbations, adaptive attacks, and review rates matched to analyst capacity.

  • Open Access

    RETRIEVAL-AUGMENTED GENERATION FOR FORENSIC LEGAL ANALYSIS: INTEGRATION OF UKRAINIAN CRIMINAL CODE WITH MOBILE DEVICE EVIDENCE

    by Taras Fedynyshyn, Оlha Partyka

    Digital forensic investigations in Ukraine require analysts to classify mobile device evidence according to the Criminal Code, a process that is time-consuming and requires deep legal expertise. This paper presents the first retrieval-augmented generation (RAG) system for Ukrainian Criminal Code analysis, focusing on Section I (Crimes Against National Security). We construct a database of 9 articles covering treason, espionage, collaboration, and sabotage offenses, and evaluate the system on 60 synthetic forensic scenarios with deterministically-derived ground truth. Our experiments compare four chunking strategies, three multilingual embedding models, and four large language models (both API-based and locally-deployed). The best retrieval configuration achieves MRR of 0.588 using multilingual-e5-large embeddings with part-level chunking. For end-to-end classification, RAG with GPT-4o-mini achieves 54.2% article identification accuracy, outperforming a few-shot prompting baseline (29.2%, p=0.03) but showing no statistically significant improvement over direct LLM prompting (52.1%, p=0.89). We argue that RAG’s primary advantage for forensic applications lies not in classification accuracy but in grounding, transparency, and governance: retrieved legal provisions are traceable and verifiable, the knowledge base can be updated without retraining, and the system supports fully local deployment where evidence cannot leave the organization. Local LLMs achieve 77% of API performance (41.7% accuracy), confirming that on-premise deployment is feasible at reduced accuracy.


  • Open Access

    Cooperative V2X-Based UAV Detection in Rural Transportation Corridors

    by Olha Partyka, Agbotiname Lucky Imoize, Chun-Ta Li

    Rural transportation corridors remain weakly instrumented for continuous low-altitude airspace monitoring. At the same time, Vehicle-to-Everything (V2X) roadside units (RSUs) are increasingly deployed for transportation safety services. This work investigates whether existing RSUs can be extended with passive, cooperative RF sensing to detect small UAVs without modifying standards-compliant ITS communications in the protected 5.9 GHz band. A calibrated simulation study evaluates corridor-scale operation under realistic propagation conditions, including terrain masking and narrowband interference. All results reported in this paper are derived from simulation and do not include field measurements or hardware prototyping. False alarm performance under diverse ISM emitters is not quantified. The results show that cooperative processing across neighboring RSUs improves epoch-level verified detection coverage compared with single-RSU sensing. Bearing variability is reduced for weak or partially masked signals. These gains result from feature-level validation across spatially separated receivers rather than deterministic signal combining. RF calibration constrains detections to physically plausible kilometer-scale ranges. The resulting angular accuracy is sufficient for early warning and track initiation, but not for precise localization. Overall, the findings indicate that existing V2X infrastructure can support supplementary early warning capability for corridor-scale airspace monitoring while preserving primary V2X safety functions.


  • Open Access

    MODERN METHODS OF ENSURING INFORMATION PROTECTION IN CYBERSECURITY SYSTEMS USING ARTIFICIAL INTELLIGENCE AND BLOCKCHAIN TECHNOLOGY

    by Oleh Harasymchuk, Ivan Opirskyy, Olha Partyka, Vitalii Susukailo, Andrian Piskozub, Dmytro Sabodashko, Sviatoslav Vasylyshyn, Anatoliy Obshta, Yevhenii Kurii, Danyil Zhuravchak, et al.

    This scientific work is devoted to the development and improvement of information protection methods to counteract unauthorized access to information activity facilities and their telecommunication networks. The conclusions of the study indicate the need to implement innovative solutions to increase the level of security in modern cyberspace. An improved algorithm for determining and transferring node hosts in the Blockchain system is proposed, which uses floating hosts to increase the adaptability of the network to external attacks. This allows to automatically close ports during scanning, making it difficult for attackers to access the system and increasing the overall level of network protection. A study of GPT models has shown their high efficiency in detecting cyberattacks on information activity facilities and their telecommunication networks. GPT-4.0 has demonstrated increased efficiency in processing and detecting various types of attacks compared to GPT-3.5, which provides faster response time and improves the overall level of security. The developed method of collecting event logs from decoys based on Blockchain provides high fault tolerance and reliability of logs, which is critically important for protecting information objects and telecommunication networks. The decentralized nature of Blockchain prevents unauthorized editing of information, creating a reliable system for storing attack data. The developed model of a dynamic system of active traps based on software decoys using Blockchain technology integrates decentralized and automatically updated attributes of traps. This increases the effectiveness of network protection, reduces the load on the infrastructure and the response time of services during attacks, which increases the channel throughput and data transfer rate. The developed mathematical description of the calculation of dynamic attributes of software decoys takes into account the capabilities of Blockchain Solana, which made it possible to model and optimize the distribution of network resources. This increased the effectiveness of protection and ensured a quick response of services during external attacks. The method of using Blockchain-based software decoys obtained in the work increases the resources required by the attacker to carry out an attack, which increases the response time of cybersecurity specialists. The use of dynamic Blockchain-based software decoys demonstrates better performance compared to static and other dynamic analogues, increasing the overall level of computer network security. The proposed cybercrime research system detects known attacks 31% faster and is able to detect unknown attacks thanks to training the Isolation Forest model. The time for analyzing cybercrimes has been significantly reduced thanks to the use of the GPT model, which provides an effective and fast response to threats.


  • Open Access

    ECOSYSTEM OF INSTALLED MOBILE APPLICATIONS FOR IDENTIFYING BEHAVIORAL GROUPS AND ASSESSING DIGITAL RISK

    by Taras Fedynyshyn, Olha Partyka

    The article investigates the ecosystem of installed mobile applications as a source of behaviorally relevant digital artifacts that can be used for user profiling and digital risk assessment in mobile device forensics. Smartphones accumulate a wide range of application-level traces that reflect user habits, interests, and activity patterns, making the structure of installed apps a valuable indirect indicator of behavioral characteristics. The study proposes a methodological framework that transforms application lists into a structured representation of user profiles based on proportional distributions of app categories. Using a dataset of anonymized screenshots collected from 100 participants, each mobile application was classified into a unified taxonomy of categories, enabling the construction of “user–category” behavioral vectors. To identify latent groups of digital behavior, k-means clustering was applied with prior normalization and validated using silhouette metrics. Dimensionality reduction through PCA allowed visualizing cluster separation and exploring structural differences between users. The results reveal two distinct behavioral groups with clearly different application ecosystems: one dominated by financial, governmental, security-oriented, and cryptocurrency apps; the other characterized by broader multimedia, utility, productivity, and personalization tools. A digital risk score was introduced to quantify potential forensic relevance based on the presence of high-risk app categories such as VPN services, anonymization tools, secure messengers, and cryptocurrency platforms. Comparative analysis shows that the first cluster demonstrates substantially higher risk levels, indicating potentially more complex forensic reconstruction scenarios. The study demonstrates that analyzing installed mobile applications enables effective behavioral segmentation, uncovering latent usage patterns and supporting forensic evaluation of digital risk. The proposed methodology offers a scalable approach for integrating application-based analysis into mobile forensics workflows and highlights directions for future work, including expanded datasets, incorporation of temporal usage patterns, and advanced machine-learning models for behavioral interpretation.

  • Open Access

    COOPERATIVE UAV DETECTION USING V2X INFRASTRUCTURE IN RURAL DEFENSE CORRIDORS: STRENGTHENING CONNECTIVITY FOR DUAL-USE APPLICATIONSADVERSARIAL TACTICS FOR DETECTION EVASION

    by Olha Partyka, Khrystyna Ambroziak

    Rural transport corridors have sparse radar coverage and constrained backhaul, which increases the risk of small-UAV incursions. A dual-use approach is proposed in which V2X roadside units (RSUs) perform cooperative RF sensing without degrading ITS functions. The architecture combines a communications subsystem for transport services with a sensing subsystem that provides multiband monitoring, sub-threshold correlation, and adaptive thresholds. The processing pipeline has three stages: local observation, inter-station correlation of weak detections, and distributed triangulation for direction and position estimation. Control messages are exchanged over the service channel with GPS time synchronization. The models account for airborne path-loss and cooperative SINR gain under interference. Validation with Monte Carlo simulations for a long corridor of evenly spaced RSUs shows higher detection probability and better azimuth accuracy than isolated nodes. Parametric studies over RSU spacing, cooperation-window size, and detection thresholds confirm consistent cooperative gain and identify boundary regimes. The system is resilient to single-node failures due to coverage overlap, but is limited for non-emitting UAVs, under heavy interference, and at corridor edges. Practical value lies in creating a cost-efficient early-warning network in sparsely populated regions and integrating with C2 systems to raise situational awareness. Planned work includes field trials, multisensor integration, and AI-based trajectory prediction.

  • Open Access

    ДОСЛІДЖЕННЯ СТІЙКОСТІ ДО АТАК ВІДТВОРЕННЯ ПРОТОКОЛІВ ДИСТАНЦІЙНОГО КЕРУВАННЯ З ВИКОРИСТАННЯМ РАДІОКАНАЛУ 433 МГЦ

    by Ольга Михайлова, Артем Стефанків

    У цій статті виявляються критичні вразливості протоколу EV1527, які широко використовуються в системах дистанційного керування, зокрема в домашніх автоматизаційних системах. Зосереджуючись на детальному аналізі структури протоколу та потенційних слабких місць, дане дослідження оцінює ризики атак повторного відтворення, які можуть здійснюватися шляхом перехоплення та повторної трансляції радіосигналів. Результати роботи демонструють значну вразливість цього протоколу до таких атак через відсутність криптографічного захисту переданих даних. У рамках цієї роботи було проведено експериментальні випробування з використанням програмно-керованого трансивера HackRF One, що дозволило відтворити атаку в контрольованих лабораторних умовах. Експерименти підтвердили теоретичні припущення щодо можливості реалізації таких атак, підкреслюючи необхідність розробки більш захищених комунікаційних протоколів. Застосування HackRF One продемонструвало, як легко зловмисники можуть перехоплювати та повторно транслювати сигнали, отримуючи несанкціонований доступ до систем дистанційного керування. У даній статті акцентується увага на важливості переходу від застарілих технологій до сучасних рішень, які включають динамічні коди та криптографію для підвищення рівня безпеки. Використання динамічних кодів, таких як технологія рухомого коду HCS301, значно ускладнює можливість атак повторного відтворення, оскільки кожна передача коду є унікальною. Це означає, що навіть у разі перехоплення сигналу зловмисник не зможе його повторити для отримання доступу. Автори рекомендують впровадження криптографічних методів, таких як технологія рухомого коду HCS301, що значно ускладнює можливість повторних атак. Запровадження таких технологій підвищує рівень безпеки та робить системи дистанційного керування більш стійкими до зловмисних дій. Крім того, наголошується на необхідності постійного оновлення та вдосконалення безпекових протоколів для захисту критичної інфраструктури. З огляду на ці результати, дана робота вказує на нагальну потребу в оновленні та вдосконаленні систем дистанційного керування, включаючи розробку нових, більш стійких до атак протоколів, особливо в контексті забезпечення безпеки об'єктів критичної інфраструктури. Інтеграція сучасних криптографічних методів є ключовим кроком для захисту від зловмисних атак та забезпечення надійної роботи систем дистанційного керування.