Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
238 results
Filters
Settings
Search Results
Conference Object A News Chain Evaluation Methodology Along With a Lattice-Based Approach for News Chain Construction(Association for Computational Linguistics (ACL), 2017) Toprak, Mustafa; Özkahraman,Ö.; Tekir, SelmaChain construction is an important requirement for understanding news and establishing the context. A news chain can be defined as a coherent set of articles that explains an event or a story. There's a lack of well-established methods in this area. In this work, we propose a methodology to evaluate the "goodness" of a given news chain and implement a concept latticebased news chain construction method by Hossain et al. The methodology part is vital as it directly affects the growth of research in this area. Our proposed methodology consists of collected news chains from different studies and two "goodness" metrics, minedge and dispersion coefficient respectively. We assess the utility of the lattice-based news chain construction method by our proposed methodology. © EMNLP 2017.All right reserved.Conference Object Forensic Analysis of Persistent Data Storages Analyzing Ntfs Formatted Drives(Karabük Üniversitesi, 2018) Özgür, Hüseyin Güven; Şahin, SerapComputational forensic is a far-reaching field for criminal and civil laws in this age. Aim of this project is to develop an educational tool to analyze persistent storage devices to find possible evidences. Evidences are found as metadata information on these drives. These metadata information are collected in a comma separated value-CSV format document. This CSV file can be imported to a database and can be easily analyzed. By the classical forensic investigator tools mostly can analyze only one media at a time, but by this way more than one digital evidence can be comparatively analyzed. Also, deleted files may hold evidences, so recovering of deleted files is an additional topic for this study. The structured codes and related documents have shared on github as an open project; to give a chance to extension of this study by new projects and we hope that the product of this study can be useful tool for computational forensic courses.Conference Object Blockchain : a Decentralized Approach To Big Data(Karabük Üniversitesi, 2018) Pehlivan Kaplan, Senem; Şahin, SerapThe blockchain technology is a hot topic and a new technology in recent years. It is not only an underlying technology for many applications like Bitcoin application, but also it is a kind of thinking including cognitive and mental processing and understanding for artificial intelligence and human enhancement. All data or services are digitized. So, this leads to deal with big data. It is a challenge to deal with big data from the perspective of performance, scalability, availability and privacy in centralized systems. Blockchain is applicable to big data and brings different perspective how to process, store, read and write data. Also, the aim of this paper is to show that better solutions are possible in a decentralized way. Even the technology is in its early stages, the blockchain technology will be in future due to its superior features. Therefore, it is better to adopt this technology as soon as possible to place in future. This paper gives a brief about how the blockchain could approach to big data and analyzes existing information regarding the challenges of big data from the side of the blockchain.Conference Object An Analysis of Rumor Spreading Fundamentals With a Case Study on Facebook(Karabük Üniversitesi, 2018) Sayin, Burcu; Şahin, SerapNowadays, the effect of social networks on people's lives is quite high. This situation gives rise to the density of information exist over social networks. That is why, analyzing the spreading pattern of information on social networks is an important issue today. The aim of this study is to technically review the background of information spreading, especially the fundamentals of rumor spreading and analyze the well-known methods on SNs. As a result, this article provides an important background for those, who works on the information spreading over SNs.Conference Object Edu-Voting: an Educational Homomorphic E-Voting System(Karabük Üniversitesi, 2018) Tekin, Leyla; Özgür, Hüseyin Güven; Sayin, Burcu; Karataş, Arzum; Şenkula, Pelin; İrtem, Emre; Şahin, SerapAs an instrument of democracy, voting is a critical issue. Although paper-based voting systems are still used commonly, e-voting systems have started to substitute under favor of improvements in the technology. This situation gives rise to need for secure, reliable, and transparent e-voting systems to make people trust. To do this, there are some security requirements that should be concerned and satisfied such as privacy, fairness, verifiability etc. This study has an educational intuition that analyzes those requirements, theoretical background information related to cryptographic schemes behind them and creates a place-based e-voting design which was implemented for kiosk voting. As a contribution, Paillier homomorphic cryptosystem is used in our system. Moreover, our study includes a detailed criticism for the implemented system in terms of chosen cryptosystems and design modules with security and e-voting requirements.Conference Object A Novel Approach To Information Spreading Models for Social Networks(International Academy, Research, and Industry Association (IARIA), 2017) Sayın, Burcu; Şahin, SerapAnalyzing and modelling the spreading of any information through a social network (SN) is an important issue in social network analysis. Proposed solutions for this issue do not only help observing the information diffusion but also serve as a valuable resource for predicting the characteristics of the network, developing network-specific advertising etc. Up-to-date approaches include probabilistic analysis of information spreading and the information cascade models. In this paper, we propose a hybrid model which considers an information spreading model, combines it with cascades and social behavior analysis. We propose a new hybrid usage approach to represent a real-world modelling for information spreading process.Article Implementation and Evaluation of Improved Secure Index Scheme Using Standard and Counting Bloom Filters(Gazi Üniversitesi, 2017) Tekin, Leyla; Şahin, SerapThis paper presents an improved Secure Index scheme as a searchable symmetric encryption technique and provides a solution that enables a secure and efficient data storage and retrieval system. Secure Index scheme, conceived by Goh, is based on standard Bloom filters (SBFs). Knowledge of the limitations of SBFs, such as handling insertions but not deletions, helps in understanding the advantages of counting Bloom filters (CBFs). Thus, we have extended this scheme by adding a new algorithm so that CBFs can also be applicable. Unlike the old scheme, our scheme can handle dynamic update of a document by updating the existing index without rebuilding it. Moreover, we give a complementary comparison of both filters in our scheme. Finally, a detailed performance evaluation shows that our scheme exhibits similar performance with regard to the query overhead and the false positive probability and is quite efficient than the old scheme with regard to the update overhead by allocating more space.Conference Object A Comparative Analysis of Two Most Recent Dynamic Community Tracking Methods(01. Izmir Institute of Technology, 2019) Karataş, Arzum; Şahin, SerapReal world networks are intrinsically dynamic, and they are mostly represented by dynamic graphs in virtual world. Analysis of these dynamic network data can give valuable information for decision support systems in many domains in criminology, politics, health, advertising and social networks etc. Community tracking is important to analyze and understand the dynamics of the group structures and predict the near futures of communities. With a successful analysis of these data, software engineering tools and decision support systems can produce more successful results for end users. In this study, we present a comparative study of two important and recent community tracking methods in terms of accuracy, algorithmic complexity and their characteristics. We use a benchmark dataset which have ground truth community information detected each time step as a test bed.Conference Object A Review on Social Bot Detection Techniques and Research Directions(Bilgi Güvenliği Derneği, 2017) Karataş, Arzum; Şahin, SerapThe rise of web services and popularity of online social networks (OSN) like Facebook, Twitter, LinkedIn etc. have led to the rise of unwelcome social bots as automated social actors. Those actors can play many malicious roles including infiltrators of human conversations, scammers, impersonators, misinformation disseminators, stock market manipulators, astroturfers, and any content polluter (spammers, malware spreaders) and so on. It is undeniable that social bots have major importance on social networks. Therefore, this paper reveals the potential hazards of malicious social bots, reviews the detection techniques within a methodological categorization and proposes avenues for future research.Conference Object Iot - Smart Contract Rule Based Secure Communication Scheme for Healthcare System(01. Izmir Institute of Technology, 2019) Kul, Aslı; Azin, Eda Nur; Özdemir, Oğulcan; Şahin, SerapNesnelerin İnterneti (IoT) gelişimini sürdüren yeni bir teknolojidir. IoT sensör cihazlarının kullanım amaçlarından biri de kritik bir alan olan tıbbi sağlık sistemlerinde hasta koşullarını izlemektir. Tıbbi cihazların, sensörlerin, uygulamaların entegrasyonu, dijital servisler ve ilgili verilerin gizliliği, doğruluğu ve kullanılabilirliği açısından kritik öneme sahiptir. Bu bildiride, IoT tabanlı sağlık sistemi yapısı tasarlanmış ve çeşitli saldırı türlerine karşı sistemin kullanılabilirliği test edilmiş Bockchain temelli akıllı sözleşme yapısının IoT sistemlerine entegre edilmesiyle sistemin davranışları Calvin ve Etherium Frameworkleri kullanılarak simüle edilmeye çalışılmıştır.