arXiv subjects

Murat Simsek

Publications and source records attributed to Murat Simsek.

At least 19 recordsLinked to original sources

arXiv2025

On-Dyn-CDA: A Real-Time Cost-Driven Task Offloading Algorithm for Vehicular Networks with Reduced Latency and Task Loss

Real-time task processing is a critical challenge in vehicular networks, where achieving low latency and minimizing dropped task ratio depend on efficient task execution. Our primary objective is to maximize the number of completed tasks while minimizing overall latency, with a particular focus on reducing number of dropped tasks. To this end, we investigate both static and dynamic versions of an optimization algorithm. The static version assumes full task availability, while the dynamic version manages tasks as they arrive. We also distinguish between online and offline cases: the online version incorporates execution time into the offloading decision process, whereas the offline version excludes it, serving as a theoretical benchmark for optimal performance. We evaluate our proposed Online Dynamic Cost-Driven Algorithm (On-Dyn-CDA) against these baselines. Notably, the static Particle Swarm Optimization (PSO) baseline assumes all tasks are transferred to the RSU and processed by the MEC, and its offline version disregards execution time, making it infeasible for real-time applications despite its optimal performance in theory. Our novel On-Dyn-CDA completes execution in just 0.05 seconds under the most complex scenario, compared to 1330.05 seconds required by Dynamic PSO. It also outperforms Dynamic PSO by 3.42% in task loss and achieves a 29.22% reduction in average latency in complex scenarios. Furthermore, it requires neither a dataset nor a training phase, and its low computational complexity ensures efficiency and scalability in dynamic environments.

cs.NI↗

arXiv2025

Meeting Deadlines in Motion: Deep RL for Real-Time Task Offloading in Vehicular Edge Networks

Vehicular Mobile Edge Computing (VEC) drives the future by enabling low-latency, high-efficiency data processing at the very edge of vehicular networks. This drives innovation in key areas such as autonomous driving, intelligent transportation systems, and real-time analytics. Despite its potential, VEC faces significant challenges, particularly in adhering to strict task offloading deadlines, as vehicles remain within the coverage area of Roadside Units (RSUs) for only brief periods. To tackle this challenge, this paper evaluates the performance boundaries of task processing by initially establishing a theoretical limit using Particle Swarm Optimization (PSO) in a static environment. To address more dynamic and practical scenarios, PSO, Deep Q-Network (DQN), and Proximal Policy Optimization (PPO) models are implemented in an online setting. The objective is to minimize dropped tasks and reduce end-to-end (E2E) latency, covering both communication and computation delays. Experimental results demonstrate that the DQN model considerably surpasses the dynamic PSO approach, achieving a 99.2% reduction in execution time. Furthermore, It leads to a reduction in dropped tasks by 2.5% relative to dynamic PSO and achieves 18.6\% lower E2E latency, highlighting the effectiveness of Deep Reinforcement Learning (DRL) in enabling scalable and efficient task management for VEC systems.

cs.NI↗

arXiv2025

Partitioned Task Offloading for Low-Latency and Reliable Task Completion in 5G MEC

The demand for MEC has increased with the rise of data-intensive applications and 5G networks, while conventional cloud models struggle to satisfy low-latency requirements. While task offloading is crucial for minimizing latency on resource-constrained User Equipment (UE), fully offloading of all tasks to MEC servers may result in overload and possible task drops. Overlooking the effect of number of dropped tasks can significantly undermine system efficiency, as each dropped task results in unfulfilled service demands and reduced reliability, directly impacting user experience and overall network performance. In this paper, we employ task partitioning, enabling partitions of task to be processed locally while assigning the rest to MEC, thus balancing the load and ensuring no task drops. This methodology enhances efficiency via Mixed Integer Linear Programming (MILP) and Cuckoo Search, resulting in effective task assignment and minimum latency. Moreover, we ensure each user's RB allocation stays within the maximum limit while keeping latency low. Experimental results indicate that this strategy surpasses both full offloading and full local processing, providing significant improvements in latency and task completion rates across diverse number of users. In our scenario, MILP task partitioning results in 24% reduction in latency compared to MILP task offloading for the maximum number of users, whereas Cuckoo search task partitioning yields 18% latency reduction in comparison with Cuckoo search task offloading.

cs.NI↗

arXiv2025

A Reliable and Efficient 5G Vehicular MEC: Guaranteed Task Completion with Minimal Latency

This paper explores the advancement of Vehicular Edge Computing (VEC) as a tailored application of Mobile Edge Computing (MEC) for the automotive industry, addressing the rising demand for real-time processing in connected and autonomous vehicles. VEC brings computational resources closer to vehicles, reducing data processing delays crucial for safety-critical applications such as autonomous driving and intelligent traffic management. However, the challenge lies in managing the high and dynamic task load generated by vehicles' data streams. We focus on enhancing task offloading and scheduling techniques to optimize both communication and computation latencies in VEC networks. Our approach involves implementing task scheduling algorithms, including First-Come, First-Served (FCFS), Shortest Deadline First (SDF), and Particle Swarm Optimization (PSO) for optimization. Additionally, we divide portions of tasks between the MEC servers and vehicles to reduce the number of dropped tasks and improve real-time adaptability. This paper also compares fixed and shared bandwidth scenarios to manage transmission efficiency under varying loads. Our findings indicate that MEC+Local (partitioning) scenario significantly outperforms MEC-only scenario by ensuring the completion of all tasks, resulting in a zero task drop ratio. The MEC-only scenario demonstrates approximately 5.65% better average end-to-end latency compared to the MEC+Local (partitioning) scenario when handling 200 tasks. However, this improvement comes at the cost of dropping a significant number of tasks (109 out of 200). Additionally, allocating shared bandwidth helps to slightly decrease transmission waiting time compared to using fixed bandwidth.

cs.NI↗

arXiv2024

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

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↗

arXiv2023

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↗

arXiv2023

Multidomain transformer-based deep learning for early detection of network intrusion

Timely response of Network Intrusion Detection Systems (NIDS) is constrained by the flow generation process which requires accumulation of network packets. This paper introduces Multivariate Time Series (MTS) early detection into NIDS to identify malicious flows prior to their arrival at target systems. With this in mind, we first propose a novel feature extractor, Time Series Network Flow Meter (TS-NFM), that represents network flow as MTS with explainable features, and a new benchmark dataset is created using TS-NFM and the meta-data of CICIDS2017, called SCVIC-TS-2022. Additionally, a new deep learning-based early detection model called Multi-Domain Transformer (MDT) is proposed, which incorporates the frequency domain into Transformer. This work further proposes a Multi-Domain Multi-Head Attention (MD-MHA) mechanism to improve the ability of MDT to extract better features. Based on the experimental results, the proposed methodology improves the earliness of the conventional NIDS (i.e., percentage of packets that are used for classification) by 5x10^4 times and duration-based earliness (i.e., percentage of duration of the classified packets of a flow) by a factor of 60, resulting in a 84.1% macro F1 score (31% higher than Transformer) on SCVIC-TS-2022. Additionally, the proposed MDT outperforms the state-of-the-art early detection methods by 5% and 6% on ECG and Wafer datasets, respectively.

cs.CR↗

arXiv2023

Host-Based Network Intrusion Detection via Feature Flattening and Two-stage Collaborative Classifier

Network Intrusion Detection Systems (NIDS) have been extensively investigated by monitoring real network traffic and analyzing suspicious activities. However, there are limitations in detecting specific types of attacks with NIDS, such as Advanced Persistent Threats (APT). Additionally, NIDS is restricted in observing complete traffic information due to encrypted traffic or a lack of authority. To address these limitations, a Host-based Intrusion Detection system (HIDS) evaluates resources in the host, including logs, files, and folders, to identify APT attacks that routinely inject malicious files into victimized nodes. In this study, a hybrid network intrusion detection system that combines NIDS and HIDS is proposed to improve intrusion detection performance. The feature flattening technique is applied to flatten two-dimensional host-based features into one-dimensional vectors, which can be directly used by traditional Machine Learning (ML) models. A two-stage collaborative classifier is introduced that deploys two levels of ML algorithms to identify network intrusions. In the first stage, a binary classifier is used to detect benign samples. All detected attack types undergo a multi-class classifier to reduce the complexity of the original problem and improve the overall detection performance. The proposed method is shown to generalize across two well-known datasets, CICIDS 2018 and NDSec-1. Performance of XGBoost, which represents conventional ML, is evaluated. Combining host and network features enhances attack detection performance (macro average F1 score) by 8.1% under the CICIDS 2018 dataset and 3.7% under the NDSec-1 dataset. Meanwhile, the two-stage collaborative classifier improves detection performance for most single classes, especially for DoS-LOIC-UDP and DoS-SlowHTTPTest, with improvements of 30.7% and 84.3%, respectively, when compared with the traditional ML XGBoost.

cs.CR↗

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↗

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↗

arXiv2022

Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition

The global Information and Communications Technology (ICT) supply chain is a complex network consisting of all types of participants. It is often formulated as a Social Network to discuss the supply chain network's relations, properties, and development in supply chain management. Information sharing plays a crucial role in improving the efficiency of the supply chain, and datasheets are the most common data format to describe e-component commodities in the ICT supply chain because of human readability. However, with the surging number of electronic documents, it has been far beyond the capacity of human readers, and it is also challenging to process tabular data automatically because of the complex table structures and heterogeneous layouts. Table Structure Recognition (TSR) aims to represent tables with complex structures in a machine-interpretable format so that the tabular data can be processed automatically. In this paper, we formulate TSR as an object detection problem and propose to generate an intuitive representation of a complex table structure to enable structuring of the tabular data related to the commodities. To cope with border-less and small layouts, we propose a cost-sensitive loss function by considering the detection difficulty of each class. Besides, we propose a novel anchor generation method using the character of tables that columns in a table should share an identical height, and rows in a table should share the same width. We implement our proposed method based on Faster-RCNN and achieve 94.79% on mean Average Precision (AP), and consistently improve more than 1.5% AP for different benchmark models.

cs.CV↗

arXiv2022

Handling big tabular data of ICT supply chains: a multi-task, machine-interpretable approach

Due to the characteristics of Information and Communications Technology (ICT) products, the critical information of ICT devices is often summarized in big tabular data shared across supply chains. Therefore, it is critical to automatically interpret tabular structures with the surging amount of electronic assets. To transform the tabular data in electronic documents into a machine-interpretable format and provide layout and semantic information for information extraction and interpretation, we define a Table Structure Recognition (TSR) task and a Table Cell Type Classification (CTC) task. We use a graph to represent complex table structures for the TSR task. Meanwhile, table cells are categorized into three groups based on their functional roles for the CTC task, namely Header, Attribute, and Data. Subsequently, we propose a multi-task model to solve the defined two tasks simultaneously by using the text modal and image modal features. Our experimental results show that our proposed method can outperform state-of-the-art methods on ICDAR2013 and UNLV datasets.

cs.CV↗

arXiv2022

Collaborative Feature Maps of Networks and Hosts for AI-driven Intrusion Detection

Intrusion Detection Systems (IDS) are critical security mechanisms that protect against a wide variety of network threats and malicious behaviors on networks or hosts. As both Network-based IDS (NIDS) or Host-based IDS (HIDS) have been widely investigated, this paper aims to present a Combined Intrusion Detection System (CIDS) that integrates network and host data in order to improve IDS performance. Due to the scarcity of datasets that include both network packet and host data, we present a novel CIDS dataset formation framework that can handle log files from a variety of operating systems and align log entities with network flows. A new CIDS dataset named SCVIC-CIDS-2021 is derived from the meta-data from the well-known benchmark dataset, CIC-IDS-2018 by utilizing the proposed framework. Furthermore, a transformer-based deep learning model named CIDS-Net is proposed that can take network flow and host features as inputs and outperform baseline models that rely on network flow features only. Experimental results to evaluate the proposed CIDS-Net under the SCVIC-CIDS-2021 dataset support the hypothesis for the benefits of combining host and flow features as the proposed CIDS-Net can improve the macro F1 score of baseline solutions by 6.36% (up to 99.89%).

cs.CR↗

arXiv2022

Prior Knowledge based Advanced Persistent Threats Detection for IoT in a Realistic Benchmark

The number of Internet of Things (IoT) devices being deployed into networks is growing at a phenomenal level, which makes IoT networks more vulnerable in the wireless medium. Advanced Persistent Threat (APT) is malicious to most of the network facilities and the available attack data for training the machine learning-based Intrusion Detection System (IDS) is limited when compared to the normal traffic. Therefore, it is quite challenging to enhance the detection performance in order to mitigate the influence of APT. Therefore, Prior Knowledge Input (PKI) models are proposed and tested using the SCVIC-APT- 2021 dataset. To obtain prior knowledge, the proposed PKI model pre-classifies the original dataset with unsupervised clustering method. Then, the obtained prior knowledge is incorporated into the supervised model to decrease training complexity and assist the supervised model in determining the optimal mapping between the raw data and true labels. The experimental findings indicate that the PKI model outperforms the supervised baseline, with the best macro average F1-score of 81.37%, which is 10.47% higher than the baseline.

cs.CR↗

arXiv2022

Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats

Despite its technological benefits, Internet of Things (IoT) has cyber weaknesses due to the vulnerabilities in the wireless medium. Machine learning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. Advanced persistent threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys to fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth to bridge the state-of-the-art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents the well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion alongside the number of attacks types detected. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.

cs.CR↗

arXiv2022

Table Structure Recognition with Conditional Attention

Tabular data in digital documents is widely used to express compact and important information for readers. However, it is challenging to parse tables from unstructured digital documents, such as PDFs and images, into machine-readable format because of the complexity of table structures and the missing of meta-information. Table Structure Recognition (TSR) problem aims to recognize the structure of a table and transform the unstructured tables into a structured and machine-readable format so that the tabular data can be further analysed by the down-stream tasks, such as semantic modeling and information retrieval. In this study, we hypothesize that a complicated table structure can be represented by a graph whose vertices and edges represent the cells and association between cells, respectively. Then we define the table structure recognition problem as a cell association classification problem and propose a conditional attention network (CATT-Net). The experimental results demonstrate the superiority of our proposed method over the state-of-the-art methods on various datasets. Besides, we investigate whether the alignment of a cell bounding box or a text-focused approach has more impact on the model performance. Due to the lack of public dataset annotations based on these two approaches, we further annotate the ICDAR2013 dataset providing both types of bounding boxes, which can be a new benchmark dataset for evaluating the methods in this field. Experimental results show that the alignment of a cell bounding box can help improve the Micro-averaged F1 score from 0.915 to 0.963, and the Macro-average F1 score from 0.787 to 0.923.

cs.CV↗

arXiv2022

Collaborative Self Organizing Map with DeepNNs for Fake Task Prevention in Mobile Crowdsensing

Mobile Crowdsensing (MCS) is a sensing paradigm that has transformed the way that various service providers collect, process, and analyze data. MCS offers novel processes where data is sensed and shared through mobile devices of the users to support various applications and services for cutting-edge technologies. However, various threats, such as data poisoning, clogging task attacks and fake sensing tasks adversely affect the performance of MCS systems, especially their sensing, and computational capacities. Since fake sensing task submissions aim at the successful completion of the legitimate tasks and mobile device resources, they also drain MCS platform resources. In this work, Self Organizing Feature Map (SOFM), an artificial neural network that is trained in an unsupervised manner, is utilized to pre-cluster the legitimate data in the dataset, thus fake tasks can be detected more effectively through less imbalanced data where legitimate/fake tasks ratio is lower in the new dataset. After pre-clustered legitimate tasks are separated from the original dataset, the remaining dataset is used to train a Deep Neural Network (DeepNN) to reach the ultimate performance goal. Pre-clustered legitimate tasks are appended to the positive prediction outputs of DeepNN to boost the performance of the proposed technique, which we refer to as pre-clustered DeepNN (PrecDeepNN). The results prove that the initial average accuracy to discriminate the legitimate and fake tasks obtained from DeepNN with the selected set of features can be improved up to an average accuracy of 0.9812 obtained from the proposed machine learning technique.

cs.NE↗