Yazar "Sahin, Canan Batur" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Detection of cyber attacks in electric vehicle charging systems using a remaining useful life generative adversarial network
    (Nature Portfolio, 2025) Tanyildiz, Hayriye; Sahin, Canan Batur; Dinler, Ozlem Batur; Migdady, Hazem; Saleem, Kashif; Smerat, Aseel; Abualigah, Laith
    Cybersecurity attacks targeting electric vehicle supply equipment (EVSE) and the broader electric vehicle (EV) ecosystem have become an escalating concern with the increasing adoption of EVs and the growing connectivity of the infrastructure supporting them. The present research aims to contribute to continuing cybersecurity studies on electric vehicle charging stations. In line with this objective, this study proposes the remaining useful life (RUL) approach to demonstrate the potential impact of estimating the remaining time of a cyber attack on EVSE and what revolutionary changes it can bring to cyber security strategies using a generative adversarial network (GAN). By taking a proactive stance, the manuscript will increase security and reduce the economic and reputational losses associated with cyber incidents. Accurate RUL estimates present valuable information about the status of the EVSE infrastructure. Thus, informed decisions on maintenance and crew scheduling are taken. To test the technique's effectiveness, we assess this approach on attack scenarios, including network and host attacks on the EV charger (Electric Vehicle Supply Equipment-EVSE) in idle and charging states. Furthermore, we assess the prediction results of different deep learning models, such as gated recurrent units (GRUs), long short-term memory (LSTM), recurrent neural networks (RNNs), convolution neural networks (CNNs), multi-layer perceptron (MLP), and dense layer integrated with generative adversarial networks (GANs), using mean absolute error (MAE), root mean square error (RMSE), mean squared error (MSE), and R-squared (R2). Afterward, we compare the error measurements with models, such as hybrid GAN-LSTM, GAN-GRU, GAN-RNN, GAN-CNN, GAN-MLP, and GAN-Dense Layer. The GAN-GRU model exhibits the highest accuracy with the lowest MAE (0.0281). On the contrary, the GAN-CNN model displays the best overall performance concerning error consistency and variance explained. According to the results, integrating GAN into these architectures improves predictive accuracy and the model's ability to identify potential attacks in advance and decreases error rates.
  • Küçük Resim Yok
    Öğe
    Improving Deceptive Patch Solutions Using Novel Deep Learning-Based Time Analysis Model for Industrial Control Systems
    (Mdpi, 2024) Tanyildiz, Hayriye; Sahin, Canan Batur; Dinler, Ozlem Batur
    Industrial control systems (ICSs) are critical components automating the processes and operations of electromechanical systems. These systems are vulnerable to cyberattacks and can be the targets of malicious activities. With increased internet connectivity and integration with the Internet of Things (IoT), ICSs become more vulnerable to cyberattacks, which can have serious consequences, such as service interruption, financial losses, and security hazards. Threat actors target these systems with sophisticated attacks that can cause devastating damage. Cybersecurity vulnerabilities in ICSs have recently led to increasing cyberattacks and malware exploits. Hence, this paper proposes to develop a security solution with dynamic and adaptive deceptive patching strategies based on studies on the use of deceptive patches against attackers in industrial control systems. Within the present study's scope, brief information on the adversarial training method and window size manipulation will be presented. It will emphasize how these methods can be integrated into industrial control systems and how they can increase cybersecurity by combining them with deceptive patch solutions. The discussed techniques represent an approach to improving the network and system security by making it more challenging for attackers to predict their targets and attack methods. The acquired results demonstrate that the suggested hybrid method improves the application of deception to software patching prediction, reflecting enhanced patch security.
  • Küçük Resim Yok
    Öğe
    Quantum-Resilient Federated Learning for Multi-Layer Cyber Anomaly Detection in UAV Systems
    (Mdpi, 2026) Sahin, Canan Batur
    Unmanned Aerial Vehicles (UAVs) are increasingly used in civilian and military applications, making their communication and control systems targets for cyber attacks. The emerging threat of quantum computing amplifies these risks. Quantum computers could break the classical cryptographic schemes used in current UAV networks. This situation underscores the need for quantum-resilient, privacy-preserving security frameworks. This paper proposes a quantum-resilient federated learning framework for multi-layer cyber anomaly detection in UAV systems. The framework combines a hybrid deep learning architecture. A Variational Autoencoder (VAE) performs unsupervised anomaly detection. A neural network classifier enables multi-class attack categorization. To protect sensitive UAV data, model training is conducted using federated learning with differential privacy. Robustness against malicious participants is ensured through Byzantine-robust aggregation. Additionally, CRYSTALS-Dilithium post-quantum digital signatures are employed to authenticate model updates and provide long-term cryptographic security. Researchers evaluated the proposed framework on a real UAV attack dataset containing GPS spoofing, GPS jamming, denial-of-service, and simulated attack scenarios. Experimental results show the system achieves 98.67% detection accuracy with only 6.8% computational overhead compared to classical cryptographic approaches, while maintaining high robustness under Byzantine attacks. The main contributions of this study are: (1) a hybrid VAE-classifier architecture enabling both zero-day anomaly detection and precise attack classification, (2) the integration of Byzantine-robust and privacy-preserving federated learning for UAV security, and (3) a practical post-quantum security design validated on real UAV communication data.
  • Küçük Resim Yok
    Öğe
    Securing UAV Swarms with Vision Transformers: A Byzantine-Robust Federated Learning Framework for Cross-Modal Intrusion Detection
    (Mdpi, 2026) Sahin, Canan Batur
    Highlights What are the main findings? The fusion of cyber and cyber-physical modalities enables high-confidence UAV intrusion detection, providing reliable decision-making for safety-critical aerial missions. The combination of Vision Transformers, GAF encoding, and Byzantine-robust FL offers a scalable, privacy-preserving solution suitable for real-world UAV swarms operating under adversarial conditions. What are the implications of the main findings? The fusion of cyber and cyber-physical modalities enables high-confidence UAV intrusion detection, providing reliable decision-making for safety-critical aerial missions. The newly introduced ReGCA aggregation method significantly improves federated robustness, maintaining 89.6% accuracy even with 40% Byzantine clients, more than 44 percentage points higher than FedAvg.Highlights What are the main findings? The fusion of cyber and cyber-physical modalities enables high-confidence UAV intrusion detection, providing reliable decision-making for safety-critical aerial missions. The combination of Vision Transformers, GAF encoding, and Byzantine-robust FL offers a scalable, privacy-preserving solution suitable for real-world UAV swarms operating under adversarial conditions. What are the implications of the main findings? The fusion of cyber and cyber-physical modalities enables high-confidence UAV intrusion detection, providing reliable decision-making for safety-critical aerial missions. The newly introduced ReGCA aggregation method significantly improves federated robustness, maintaining 89.6% accuracy even with 40% Byzantine clients, more than 44 percentage points higher than FedAvg.Abstract The increasing deployment of uncrewed aerial vehicles (UAVs) in cyber-physical and safety-critical missions has amplified the need for intrusion detection systems that are accurate, privacy-preserving, and resilient to adversarial manipulation. In this paper, we propose CM-BRF-ViT, a Cross-Modal Byzantine-Robust Federated Vision Transformer framework for UAV intrusion detection that jointly addresses heterogeneous attack modeling, distributed learning security, and adaptive decision fusion. The proposed framework integrates Gramian Angular Field (GAF) transformations with Vision Transformer (ViT) architectures to effectively convert tabular network and cyber-physical features into discriminative visual representations suitable for attention-based learning. To enable privacy-preserving collaboration across distributed UAV nodes, CM-BRF-ViT operates within a federated learning paradigm and introduces Reference-GAF Consistency Aggregation (ReGCA). This novel Byzantine-robust aggregation mechanism jointly measures prediction consistency and feature-level semantic consistency using a trusted reference set and MAD-based robust weighting. Unlike conventional defenses that rely solely on parameter-space filtering, ReGCA supervises model updates at both behavioral and representation levels, significantly enhancing robustness against malicious clients. In addition, a learnable cross-modal fusion head is developed to adaptively combine attack probabilities derived from cyber and cyber-physical modalities, allowing the framework to exploit complementary threat signatures across layers. Extensive experiments conducted on the UAVIDS-2025 and Cyber-Physical datasets demonstrate that the proposed method achieves 97.1% detection accuracy for UAV network traffic and 78.5% for cyber-physical data, with a fused detection AUC of 0.993. Under adversarial settings, CM-BRF-ViT preserves 89. 6% accuracy with up to 40% Byzantine clients, outperforming FedAvg by more than 44 percentage points. Ablation studies further confirm that ReGCA, cross-modal fusion, and ViT-based representation learning contribute complementary performance gains over baseline federated and centralized approaches. These results demonstrate that CM-BRF-ViT provides a robust, adaptive, and privacy-aware intrusion detection solution for UAV systems, making it well-suited for deployment in adversarial and resource-constrained aerial networks.
  • Küçük Resim Yok
    Öğe
    Semantic-based vulnerability detection by functional connectivity of gated graph sequence neural networks
    (Springer, 2023) Sahin, Canan Batur
    In computer security, semantic learning is helpful in understanding vulnerability requirements, realizing source code semantics, and constructing vulnerability knowledge. Nevertheless, learning how to extract and select the most valuable features for software vulnerability detection remains difficult. In this paper, we first derive a subset of vulnerability knowledge representations from the Functional Connectivity (FC) of Graph Gated Sequence Neural Networks (GGNNs). The Gated Graph Sequence Neural Networks can be utilized to capture the long-term dependency to understand a high-level representation of potential vulnerabilities in order to detect vulnerabilities on a target project. Studying functional connectivity-based Graph Neural Networks ensures our deep understanding of the operation of sequence graph networks as highly complex interconnected systems. This ensures that the model focuses on vulnerability-related code, which makes it more appropriate for vulnerability mining tasks. Which constructs a composite semantic code property graph for code representation based on the causes of vulnerabilities. The experimental findings indicate that the suggested Model can select relevant discriminative features and achieve superior performance than benchmark methods.
  • Küçük Resim Yok
    Öğe
    Synthetic Data Augmentation for Imbalanced Tabular Protein Subcellular Localization: A Comparative Study of SMOTE, CTGAN, TVAE, and TabDDPM Methods
    (Mdpi, 2026) Gunduz, Ali Fatih; Sahin, Canan Batur
    Class imbalance is a persistent challenge in supervised machine learning, particularly in biological datasets where minority classes represent functionally critical categories. Synthetic data generation has emerged as a principal strategy for mitigating this problem, yet systematic comparisons of classical and modern deep generative approaches remain limited. This study presents a comprehensive benchmark evaluation of four synthetic data generation methods-SMOTE, CTGAN, TVAE, and TabDDPM-across two well-established biological datasets from the UCI Machine Learning Repository: the E. coli protein localization dataset (307 samples, 6 features, 4 classes) and the yeast protein localization dataset (1299 samples, 8 features, 4 classes). Synthetic data quality was rigorously assessed using a multi-dimensional evaluation framework encompassing distributional fidelity (Fr & eacute;chet Distance, Wasserstein Distance), machine learning utility (Train-on-Synthetic-Test-on-Real and Train-on-Real-Test-on-Real protocols using XGBoost version 3.2.0, Logistic Regression, Support Vector Machines, and Random Forest), and distinguishability (Classifier Two-Sample Test). The datasets are rather imbalanced. During the experiments, the dataset size increased to three times its original size while preserving the imbalanced class-sample ratio. To evaluate the quality of synthetic data, the max(AUC,1-AUC) score is proposed. This score is inversely proportional to classification performance, indicating that synthetic data are not easily distinguishable from real data. Per-class analysis reveals that minority classes remain the primary challenge across all generative methods. SMOTE and TabDDPM obtained the highest predictive utility F1-scores across both datasets. TVAE offers the strongest distributional fidelity among deep generative models, producing synthetic samples that are most difficult to distinguish from real data (lowest C2ST scores). CTGAN exhibits significant performance degradation on both small- and medium-scale datasets, with F1 utility ratios below 0.50.