arXiv subjects

Burak Kantarci

Publications and source records attributed to Burak Kantarci.

At least 55 records · Page 3Linked to original sources

arXiv2025

A Two-Stage CAE-Based Federated Learning Framework for Efficient Jamming Detection in 5G Networks

Cyber-security for 5G networks is drawing notable attention due to an increase in complex jamming attacks that could target the critical 5G Radio Frequency (RF) domain. These attacks pose a significant risk to heterogeneous network (HetNet) architectures, leading to degradation in network performance. Conventional machine-learning techniques for jamming detection rely on centralized training while increasing the odds of data privacy. To address these challenges, this paper proposes a decentralized two-stage federated learning (FL) framework for jamming detection in 5G femtocells. Our proposed distributed framework encompasses using the Federated Averaging (FedAVG) algorithm to train a Convolutional Autoencoder (CAE) for unsupervised learning. In the second stage, we use a fully connected network (FCN) built on the pre-trained CAE encoder that is trained using Federated Proximal (FedProx) algorithm to perform supervised classification. Our experimental results depict that our proposed framework (FedAVG and FedProx) accomplishes efficient training and prediction across non-IID client datasets without compromising data privacy. Specifically, our framework achieves a precision of 0.94, recall of 0.90, F1-score of 0.92, and an accuracy of 0.92, while minimizing communication rounds to 30 and achieving robust convergence in detecting jammed signals with an optimal client count of 6.

cs.CR↗

arXiv2025

Active RIS-Assisted URLLC NOMA-Based 5G Network with FBL under Jamming Attacks

In this paper, we tackle the challenge of jamming attacks in Ultra-Reliable Low Latency Communication (URLLC) within Non-Orthogonal Multiple Access (NOMA)-based 5G networks under Finite Blocklength (FBL) conditions. We introduce an innovative approach that employs Reconfigurable Intelligent Surfaces (RIS) with active elements to enhance energy efficiency while ensuring reliability and meeting latency requirements. Our approach incorporates the traffic model, making it practical for real-world scenarios with dynamic traffic loads. We thoroughly analyze the impact of blocklength and packet arrival rate on network performance metrics and investigate the optimal amplitude value and number of RIS elements. Our results indicate that increasing the number of RIS elements from 4 to 400 can improve signal-to-jamming-plus-noise ratio (SJNR) by 13.64\%. Additionally, optimizing blocklength and packet arrival rate can achieve a 31.68% improvement in energy efficiency and reduced latency. These findings underscore the importance of optimized settings for effective jamming mitigation.

cs.CR↗

arXiv2025

Joint Optimization of Completion Ratio and Latency of Offloaded Tasks with Multiple Priority Levels in 5G Edge

Multi-Access Edge Computing (MEC) is widely recognized as an essential enabler for applications that necessitate minimal latency. However, the dropped task ratio metric has not been studied thoroughly in literature. Neglecting this metric can potentially reduce the system's capability to effectively manage tasks, leading to an increase in the number of eliminated or unprocessed tasks. This paper presents a 5G-MEC task offloading scenario with a focus on minimizing the dropped task ratio, computational latency, and communication latency. We employ Mixed Integer Linear Programming (MILP), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) to optimize the latency and dropped task ratio. We conduct an analysis on how the quantity of tasks and User Equipment (UE) impacts the ratio of dropped tasks and the latency. The tasks that are generated by UEs are classified into two categories: urgent tasks and non-urgent tasks. The UEs with urgent tasks are prioritized in processing to ensure a zero-dropped task ratio. Our proposed method improves the performance of the baseline methods, First Come First Serve (FCFS) and Shortest Task First (STF), in the context of 5G-MEC task offloading. Under the MILP-based approach, the latency is reduced by approximately 55% compared to GA and 35% compared to PSO. The dropped task ratio under the MILP-based approach is reduced by approximately 70% compared to GA and by 40% compared to PSO.

cs.NI↗

arXiv2024

Scalability Assurance in SFC provisioning via Distributed Design for Deep Reinforcement Learning

High-quality Service Function Chaining (SFC) provisioning is provided by the timely execution of Virtual Network Functions (VNFs) in a defined sequence. Advanced Deep Reinforcement Learning (DRL) solutions are utilized in many studies to contribute to fast and reliable autonomous SFC provisioning. However, under a large-scale network environment, centralized solutions might struggle to provide efficient outcomes when handling massive demands with stringent End-to-End (E2E) delay constraints. Therefore, in this paper, a novel distributed SFC provisioning framework is proposed, where the network is divided into several clusters. Each cluster has a dedicated local agent with a DRL module to handle the SFC provisioning of demands in that cluster. Also, there is a general agent that can communicate with local agents to handle the requests beyond their capacity. The DRL module of local agents can be applied under different configurations of clusters independent of different numbers of data centers and logical links in each cluster. Simulation results demonstrate that utilizing the proposed distributed framework offers up to 60% improvements in the acceptance ratio of service requests in comparison to the centralized approach while minimizing the E2E delay of accepted requests.

cs.NI↗

arXiv2024

GenAI Assistance for Deep Reinforcement Learning-based VNF Placement and SFC Provisioning in 5G Cores

Virtualization technology, Network Function Virtualization (NFV), gives flexibility to communication and 5G core network technologies for dynamic and efficient resource allocation while reducing the cost and dependability of the physical infrastructure. In the NFV context, Service Function Chain (SFC) refers to the ordered arrangement of various Virtual Network Functions (VNFs). To provide an automated SFC provisioning algorithm that satisfies high demands of SFC requests having ultra-reliable and low latency communication (URLLC) requirements, in the literature, Artificial Intelligence (AI) modules and Deep Reinforcement Learning (DRL) algorithms are investigated in detail. This research proposes a generative Variational Autoencoder (VAE) assisted advanced-DRL module for handling SFC requests in a dynamic environment where network configurations and request amounts can be changed. Using the hybrid approach, including generative VAE and DRL, the algorithm leverages several advantages, such as dimensionality reduction, better generalization on the VAE side, exploration, and trial-error learning from the DRL model. Results show that GenAI-assisted DRL surpasses the state-of-the-art model of DRL in SFC provisioning in terms of SFC acceptance ratio, E2E delay, and throughput maximization.

cs.NI↗

arXiv2024

The impact of mobility, beam sweeping and smart jammers on security vulnerabilities of 5G cells

The vulnerability of 5G networks to jamming attacks has emerged as a significant concern. This paper contributes in two primary aspects. Firstly, it investigates the effect of a multi-jammer on 5G cell metrics, specifically throughput and goodput. The investigation is conducted within the context of a mobility model for user equipment (UE), with a focus on scenarios involving connected vehicles (CVs) engaged in a mission. Secondly, the vulnerability of synchronization signal block (SSB) components is examined concerning jamming power and beam sweeping. Notably, the study reveals that increasing jamming power beyond 40 dBm in our specific scenario configuration no longer decreases network throughput due to the re-transmission of packets through the hybrid automatic repeat request (HARQ) process. Furthermore, it is observed that under the same jamming power, the physical downlink shared channel (PDSCH) is more vulnerable than the primary synchronization signal (PSS) and secondary synchronization signal (SSS). However, a smart jammer can disrupt the cell search process by injecting less power and targeting PSS-SSS or physical broadcast channel (PBCH) data compared to a barrage jammer. On the other hand, beam sweeping proves effective in mitigating the impact of a smart jammer, reducing the error vector magnitude root mean square from 51.59% to 23.36% under the same jamming power.

cs.CR↗

arXiv2024

Efficient Prompting for LLM-based Generative Internet of Things

Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. However, open-source LLMs usually have more limitations regarding their performance, such as their arithmetic calculation and reasoning capacities, and practical systems of applying LLMs to IoT have yet to be well-explored. Therefore, we propose a LLM-based Generative IoT (GIoT) system deployed in the local network setting in this study. To alleviate the limitations of LLMs and provide service with competitive performance, we apply prompt engineering methods to enhance the capacities of the open-source LLMs, design a Prompt Management Module and a Post-processing Module to manage the tailored prompts for different tasks and process the results generated by the LLMs. To demonstrate the effectiveness of the proposed system, we discuss a challenging Table Question Answering (Table-QA) task as a case study of the proposed system, as tabular data is usually more challenging than plain text because of their complex structures, heterogeneous data types and sometimes huge sizes. We conduct comprehensive experiments on two popular Table-QA datasets, and the results show that our proposal can achieve competitive performance compared with state-of-the-art LLMs, demonstrating that the proposed LLM-based GIoT system can provide competitive performance with tailored prompting methods and is easily extensible to new tasks without training.

cs.AI↗

arXiv2024

A Novel Joint DRL-Based Utility Optimization for UAV Data Services

In this paper, we propose a novel joint deep reinforcement learning (DRL)-based solution to optimize the utility of an uncrewed aerial vehicle (UAV)-assisted communication network. To maximize the number of users served within the constraints of the UAV's limited bandwidth and power resources, we employ deep Q-Networks (DQN) and deep deterministic policy gradient (DDPG) algorithms for optimal resource allocation to ground users with heterogeneous data rate demands. The DQN algorithm dynamically allocates multiple bandwidth resource blocks to different users based on current demand and available resource states. Simultaneously, the DDPG algorithm manages power allocation, continuously adjusting power levels to adapt to varying distances and fading conditions, including Rayleigh fading for non-line-of-sight (NLoS) links and Rician fading for line-of-sight (LoS) links. Our joint DRL-based solution demonstrates an increase of up to 41% in the number of users served compared to scenarios with equal bandwidth and power allocation.

cs.NI↗

arXiv2024

A New Realistic Platform for Benchmarking and Performance Evaluation of DRL-Driven and Reconfigurable SFC Provisioning Solutions

Service Function Chain (SFC) provisioning stands as a pivotal technology in the realm of 5G and future networks. Its essence lies in orchestrating VNFs (Virtual Network Functions) in a specified sequence for different types of SFC requests. Efficient SFC provisioning requires fast, reliable, and automatic VNFs' placements, especially in a network where massive amounts of SFC requests are generated having ultra-reliable and low latency communication (URLLC) requirements. Although much research has been done in this area, including Artificial Intelligence (AI) and Machine Learning (ML)-based solutions, this work presents an advanced Deep Reinforcement Learning (DRL)-based simulation model for SFC provisioning that illustrates a realistic environment. The proposed simulation platform can handle massive heterogeneous SFC requests having different characteristics in terms of VNFs chain, bandwidth, and latency constraints. Also, the model is flexible to apply to networks having different configurations in terms of the number of data centers (DCs), logical connections among DCs, and service demands. The simulation model components and the workflow of processing VNFs in the SFC requests are described in detail. Numerical results demonstrate that using this simulation setup and proposed algorithm, a realistic SFC provisioning can be achieved with an optimal SFC acceptance ratio while minimizing the E2E latency and resource consumption.

cs.NI↗

arXiv2024

Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses

The ongoing deployment of the fifth generation (5G) wireless networks constantly reveals limitations concerning its original concept as a key driver of Internet of Everything (IoE) applications. These 5G challenges are behind worldwide efforts to enable future networks, such as sixth generation (6G) networks, to efficiently support sophisticated applications ranging from autonomous driving capabilities to the Metaverse. Edge learning is a new and powerful approach to training models across distributed clients while protecting the privacy of their data. This approach is expected to be embedded within future network infrastructures, including 6G, to solve challenging problems such as resource management and behavior prediction. This survey article provides a holistic review of the most recent research focused on edge learning vulnerabilities and defenses for 6G-enabled IoT. We summarize the existing surveys on machine learning for 6G IoT security and machine learning-associated threats in three different learning modes: centralized, federated, and distributed. Then, we provide an overview of enabling emerging technologies for 6G IoT intelligence. Moreover, we provide a holistic survey of existing research on attacks against machine learning and classify threat models into eight categories, including backdoor attacks, adversarial examples, combined attacks, poisoning attacks, Sybil attacks, byzantine attacks, inference attacks, and dropping attacks. In addition, we provide a comprehensive and detailed taxonomy and a side-by-side comparison of the state-of-the-art defense methods against edge learning vulnerabilities. Finally, as new attacks and defense technologies are realized, new research and future overall prospects for 6G-enabled IoT are discussed.

cs.CR↗

arXiv2024

Bypassing a Reactive Jammer via NOMA-Based Transmissions in Critical Missions

Wireless networks can be vulnerable to radio jamming attacks. The quality of service under a jamming attack is not guaranteed and the service requirements such as reliability, latency, and effective rate, specifically in mission-critical military applications, can be deeply affected by the jammer's actions. This paper analyzes the effect of a reactive jammer. Particularly, reliability, average transmission delay, and the effective sum rate (ESR) for a NOMA-based scheme with finite blocklength transmissions are mathematically derived taking the detection probability of the jammer into account. Furthermore, the effect of UEs' allocated power and blocklength on the network metrics is explored. Contrary to the existing literature, results show that gNB can mitigate the impact of reactive jamming by decreasing transmit power, making the transmissions covert at the jammer side. Finally, an optimization problem is formulated to maximize the ESR under reliability, delay, and transmit power constraints. It is shown that by adjusting the allocated transmit power to UEs by gNB, the gNB can bypass the jammer effect to fulfill the 0.99999 reliability and the latency of 5ms without the need for packet re-transmission.

cs.CR↗

arXiv2024

On the Interplay Between Network Metrics and Performance of Mobile Edge Offloading

Multi-Access Edge Computing (MEC) emerged as a viable computing allocation method that facilitates offloading tasks to edge servers for efficient processing. The integration of MEC with 5G, referred to as 5G-MEC, provides real-time processing and data-driven decision-making in close proximity to the user. The 5G-MEC has gained significant recognition in task offloading as an essential tool for applications that require low delay. Nevertheless, few studies consider the dropped task ratio metric. Disregarding this metric might possibly undermine system efficiency. In this paper, the dropped task ratio and delay has been minimized in a realistic 5G-MEC task offloading scenario implemented in NS3. We utilize Mixed Integer Linear Programming (MILP) and Genetic Algorithm (GA) to optimize delay and dropped task ratio. We examined the effect of the number of tasks and users on the dropped task ratio and delay. Compared to two traditional offloading schemes, First Come First Serve (FCFS) and Shortest Task First (STF), our proposed method effectively works in 5G-MEC task offloading scenario. For MILP, the dropped task ratio and delay has been minimized by 20% and 2ms compared to GA.

cs.NI↗

arXiv2024

Deep Dict: Deep Learning-based Lossy Time Series Compressor for IoT Data

We propose Deep Dict, a deep learning-based lossy time series compressor designed to achieve a high compression ratio while maintaining decompression error within a predefined range. Deep Dict incorporates two essential components: the Bernoulli transformer autoencoder (BTAE) and a distortion constraint. BTAE extracts Bernoulli representations from time series data, reducing the size of the representations compared to conventional autoencoders. The distortion constraint limits the prediction error of BTAE to the desired range. Moreover, in order to address the limitations of common regression losses such as L1/L2, we introduce a novel loss function called quantized entropy loss (QEL). QEL takes into account the specific characteristics of the problem, enhancing robustness to outliers and alleviating optimization challenges. Our evaluation of Deep Dict across ten diverse time series datasets from various domains reveals that Deep Dict outperforms state-of-the-art lossy compressors in terms of compression ratio by a significant margin by up to 53.66%.

eess.SP↗

arXiv2024

Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images

Table Structure Recognition (TSR) is a widely discussed task aiming at transforming unstructured table images into structured formats, such as HTML sequences, to make text-only models, such as ChatGPT, that can further process these tables. One type of solution is using detection models to detect table components, such as columns and rows, then applying a rule-based post-processing method to convert detection results into HTML sequences. However, existing detection-based models usually cannot perform as well as other types of solutions regarding cell-level TSR metrics, such as TEDS, and the underlying reasons limiting the performance of these models on the TSR task are also not well-explored. Therefore, we revisit existing detection-based models comprehensively and explore the underlying reasons hindering these models' performance, including the improper problem definition, the mismatch issue of detection and TSR metrics, the characteristics of detection models, and the impact of local and long-range features extraction. Based on our analysis and findings, we apply simple methods to tailor a typical two-stage detection model, Cascade R-CNN, for the TSR task. The experimental results show that the tailored Cascade R-CNN based model can improve the base Cascade R-CNN model by 16.35\% on the FinTabNet dataset regarding the structure-only TEDS, outperforming other types of state-of-the-art methods, demonstrating that our findings can be a guideline for improving detection-based TSR models and that a purely detection-based solution is competitive with other types of solutions, such as graph-based and image-to-sequence solutions.

cs.CV↗

arXiv2024

Adversarial Machine Learning-Enabled Anonymization of OpenWiFi Data

Data privacy and protection through anonymization is a critical issue for network operators or data owners before it is forwarded for other possible use of data. With the adoption of Artificial Intelligence (AI), data anonymization augments the likelihood of covering up necessary sensitive information; preventing data leakage and information loss. OpenWiFi networks are vulnerable to any adversary who is trying to gain access or knowledge on traffic regardless of the knowledge possessed by data owners. The odds for discovery of actual traffic information is addressed by applied conditional tabular generative adversarial network (CTGAN). CTGAN yields synthetic data; which disguises as actual data but fostering hidden acute information of actual data. In this paper, the similarity assessment of synthetic with actual data is showcased in terms of clustering algorithms followed by a comparison of performance for unsupervised cluster validation metrics. A well-known algorithm, K-means outperforms other algorithms in terms of similarity assessment of synthetic data over real data while achieving nearest scores 0.634, 23714.57, and 0.598 as Silhouette, Calinski and Harabasz and Davies Bouldin metric respectively. On exploiting a comparative analysis in validation scores among several algorithms, K-means forms the epitome of unsupervised clustering algorithms ensuring explicit usage of synthetic data at the same time a replacement for real data. Hence, the experimental results aim to show the viability of using CTGAN-generated synthetic data in lieu of publishing anonymized data to be utilized in various applications.

cs.NI↗

arXiv2023

On the Impact of CDL and TDL Augmentation for RF Fingerprinting under Impaired Channels

Cyber-physical systems have recently been used in several areas (such as connected and autonomous vehicles) due to their high maneuverability. On the other hand, they are susceptible to cyber-attacks. Radio frequency (RF) fingerprinting emerges as a promising approach. This work aims to analyze the impact of decoupling tapped delay line and clustered delay line (TDL+CDL) augmentation-driven deep learning (DL) on transmitter-specific fingerprints to discriminate malicious users from legitimate ones. This work also considers 5G-only-CDL, WiFi-only-TDL augmentation approaches. RF fingerprinting models are sensitive to changing channels and environmental conditions. For this reason, they should be considered during the deployment of a DL model. Data acquisition can be another option. Nonetheless, gathering samples under various conditions for a train set formation may be quite hard. Consequently, data acquisition may not be feasible. This work uses a dataset that includes 5G, 4G, and WiFi samples, and it empowers a CDL+TDL-based augmentation technique in order to boost the learning performance of the DL model. Numerical results show that CDL+TDL, 5G-only-CDL, and WiFi-only-TDL augmentation approaches achieve 87.59%, 81.63%, 79.21% accuracy on unobserved data while TDL/CDL augmentation technique and no augmentation approach result in 77.81% and 74.84% accuracy on unobserved data, respectively.

eess.SP↗

arXiv2023

Revisiting Table Detection Datasets for Visually Rich Documents

Table Detection has become a fundamental task for visually rich document understanding with the surging number of electronic documents. However, popular public datasets widely used in related studies have inherent limitations, including noisy and inconsistent samples, limited training samples, and limited data sources. These limitations make these datasets unreliable to evaluate the model performance and cannot reflect the actual capacity of models. Therefore, this study revisits some open datasets with high-quality annotations, identifies and cleans the noise, and aligns the annotation definitions of these datasets to merge a larger dataset, termed Open-Tables. Moreover, to enrich the data sources, we propose a new ICT-TD dataset using the PDF files of Information and Communication Technologies (ICT) commodities, a different domain containing unique samples that hardly appear in open datasets. To ensure the label quality of the dataset, we annotated the dataset manually following the guidance of a domain expert. The proposed dataset is challenging and can be a sample of actual cases in the business context. We built strong baselines using various state-of-the-art object detection models. Our experimental results show that the domain differences among existing open datasets are minor despite having different data sources. Our proposed Open-Tables and ICT-TD can provide a more reliable evaluation for models because of their high quality and consistent annotations. Besides, they are more suitable for cross-domain settings. Our experimental results show that in the cross-domain setting, benchmark models trained with cleaned Open-Tables dataset can achieve 0.6\%-2.6\% higher weighted average F1 than the corresponding ones trained with the noisy version of Open-Tables, demonstrating the reliability of the proposed datasets. The datasets are public available.

cs.IR↗

arXiv2023

Table Detection for Visually Rich Document Images

Table Detection (TD) is a fundamental task to enable visually rich document understanding, which requires the model to extract information without information loss. However, popular Intersection over Union (IoU) based evaluation metrics and IoU-based loss functions for the detection models cannot directly represent the degree of information loss for the prediction results. Therefore, we propose to decouple IoU into a ground truth coverage term and a prediction coverage term, in which the former can be used to measure the information loss of the prediction results. Besides, considering the sparse distribution of tables in document images, we use SparseR-CNN as the base model and further improve the model by using Gaussian Noise Augmented Image Size region proposals and many-to-one label assignments. Results under comprehensive experiments show that the proposed method can consistently outperform state-of-the-art methods with different IoU-based metrics under various datasets and demonstrate that the proposed decoupled IoU loss can enable the model to alleviate information loss.

cs.CV↗