Thesis defense

thesis defense

Ali Mert Ertuğrul, Interpretable Spatio-Temporal Networks for Modeling and Forecasting Societal Events

PhD Candidate: Ali Mert Ertuğrul
Program: Information Systems
Date: 20.11.2019 15:30
Place: Conference Hall 1

Abstract: The relationships between individual activities and societal events (e.g. migrations, social movements) are complex due to the various social, temporal and spatial factors. Understanding such relationships in the context of various societal events such as street protests and opioid crisis, and forecasting these events is important as they have great impacts on public policies and supporting decision making of authorities. In this thesis, novel, spatio-temporal, deep neural networks are proposed (i) to forecast societal events and (ii) to help examine the relationships between societal events and their social and geographical contexts. The proposed models are designed to model the complex interactions between local (observed from within a location) and global (observed from all locations) activities by incorporating a new design of attentional networks. They are capable of forecasting the occurrence of future societal events and allow for interpreting what features, from which places, and how they contribute to event forecasting. Within the scope of this thesis, extensive experiments are conducted to evaluate the proposed networks on two different types of population-level societal events, namely social movements and opioid overdoses, with multiple datasets. The results indicate that the proposed models achieve superior forecasting performance than the compared methods. Also, they provide meaningful interpretations in terms of (i) what local and global activity features are more predictive, (ii) what locations have more salient contributions, and (iii) how these locations contribute to forecasting the subsequent events.

Announcement Category

Doğan Doğanay : Identifying Factors Affecting Auditors’ Adoption of Computer Assisted Audit Tools and Techniques (CAATTs): An Empirical Investigation

Msc. Candidate: Doğan Doğanay

Program: Information Systems

Date: 06.09.2019 11:00 a.m

Place: B-116

Abstract: Increasing usage of Information Technologies in organizations both private and public, audit activities has become more complicated for audit bodies. At this stage, Computer Assisted Audit Tools and Techniques (CAATTs) provide many advantages to auditors to carry out their tasks in an effective and efficient manner in such an environment and expansion of CAATTs usage plays an important role for auditors and organizations. In order to increase usage of CAATTs, it is critical to know what factors are significantly affecting the adoption decision. In this respect, the main objective of this paper is to reveal the factors affecting the Acceptance or Adoption of CAATTs by auditors. For this purpose, this study empirically explores the variables impacting use of CAATTs by Turkish auditors. As a result, a CAATTs adoption model is created in this study. In the scope of this study, firstly, studies related with the adoption of CAATTs were reviewed from 2000 to end of February 2019. This review gives information about past research on the field. At the end of the literature review, most significant factors affecting the CAATTs adoption are identified. Then, a technology adoption model and related hypotheses are proposed in the light of information derived from literature review. To test the hypotheses a quantitative method (questionnaire) is followed. Data is collected from auditors from Turkey. The model is tested using Structural Equation Modelling with Partial Least Squares (SEM-PLS). Inter-factor relationships are also introduced to the model after outcomes are obtained. At the end, the model's final version is developed and the most significant factors affecting the adoption of CAATTs by auditors are revealed.

 

Announcement Category

Mutlu Erhan : EVALUATION OF THE IOT DESIGNS AND PRODUCTS IN THE CONTEXT OF SECURITY AND PRIVACY

Msc. Candidate: Mutlu Erhan

Program: Information Systems

Date: 04.09.2019 16:15 p.m

Place: A-108

Abstract: Security and privacy issues in the Internet of Things (IoT) have received much attention in recent years because of the attacks, which have increased both in quantity and diversity. Many studies have been done to make the IoT ecosystem more secure, and these have managed to ease some risks partially by presenting security frameworks or basic standards. However; presented frameworks or standards have not been accepted by all the stakeholders in the IoT ecosystem and have not been able to provide solutions for design and evaluation. One way to decrease the risks posed by the vulnerabilities is to increase awareness of the stakeholders for security and privacy issues in the IoT system via providing simple, usable and enough protection skills, methods, standards and framework models in a design and evaluation environment.

Previous studies have analyzed reference framework models, presented security threats as a layered structure and managed to demonstrate the visibility of risks with a model of building blocks. However, besides the demonstration of the general security problems in the IoT stack, little attention was given to the generation of an evaluation environment and its usability. This study aims to present an environment, named as the Secure IoT Design and Evaluation Environment (SIDE), for IoT system developers to evaluate their products security risks against related vulnerabilities and to correct their deficits in the ecosystem, especially at the design phase. It was shown that the SIDE is practical and highly usable in identifying threats related to a design decision and evaluating the security of alternative solutions based on their known vulnerabilities.

Announcement Category

Fatma Mutlu : The Right Person to the Right Job: Developing a Two-Sided Matching Methodology Based on Real Employee Data

Msc. Candidate: Fatma Mutlu

Program: Information Systems

Date: 03.09.2019 14:00 p.m

Place: A-108

Abstract: Talented employees is one of the most important factors that carries companies to success in today's business world. However, making employees work in the right position so that it is compatible with their ability, nature and capacity is a much more important factor for success. Ignoring this situation poses an obstacle to work in an efficient and effective way for the companies. The objective of this thesis is to provide a methodology to match employees with the right position by considering both technical and behavioral competencies. In this study, both the needs of the employees and requirements of positions are taken into considerations and weights of them are calculated. Then a multi objective optimization model is developed to make both employee and position satisfactory degree the most. Results of this study are used for the purpose of achieving high job satisfaction and productivity by improving bilateral matching evaluation of both workers and positions. This study also may be used as guidance in the planning of businesses related training and development activities. To show the applicability and contribution of the methodology developed, it is validated using real life data.

Announcement Category

Gürol Canbek : Multi-Perspective Analysis and Systematic Benchmarking for Binary-Classification Performance Evaluation Instruments

PhD. Candidate: Gürol Canbek

Program: Information Systems

Date: 02.09.2019 13:00 p.m

Place: Conference Hall 01

Abstract: This thesis proposes novel methods to analyze and benchmark binary-classification performance evaluation instruments. It addresses critical problems found in the literature, clarifies terminology and distinguishes instruments as measure, metric, and as a new category indicator for the first time. The multi-perspective analysis introduces novel concepts such as canonical form, geometry, duality, complementation, dependency, and leveling with formal definitions as well as two new basic instruments. An indicator named Accuracy Barrier is also proposed and tested in re-evaluating performances of surveyed machine-learning classifications. An exploratory table is designed to represent all the concepts for over 50 instruments. The table’s real use cases such as domain-specific metrics reporting are demonstrated. Furthermore, this thesis proposes a systematic benchmarking method comprising 3 stages to assess metrics’ robustness over new concepts such as meta-metrics (metrics about metrics) and metric-space. Benchmarking 13 metrics reveals critical issues especially in accuracy, F1, and normalized mutual information conventional metrics and identifies Matthews Correlation Coefficient as the most robust metric. The benchmarking method is evaluated with the literature. Additionally, this thesis formally demonstrates publication and confirmation biases due to reporting non-robust metrics. Finally, this thesis gives recommendations on precise and concise performance evaluation, comparison, and reporting. The developed software library, analysis/benchmarking platform, visualization and calculator/dashboard tools, and datasets were also released online. This research is expected to re-establish and facilitate classification performance evaluation domain as well as contribute towards responsible open research in performance evaluation to use the most robust and objective instruments.

Announcement Category

Mustafa Mert Karataş : Malicious User Input Detection on Web-Based Attacks with the Negative Selection Algorithm

Msc. Candidate: Mustafa Mert Karataş

Program: Cyber Security

Date: 09.09.2019 13:00 p.m

Place: A-212

Abstract: The human body is exposed to several pathogens during its lifetime. HIS(Human Immune System) is responsible to protect the body from different pathogens. HIS has two distinct response systems to these outsiders, which are; innate and adaptive immune systems. While the innate system takes general actions to the intruding pathogens, the adaptive immune system eradicates them by its special cells. T-Cells, one of the defined adaptive immunity cells, are created in the thymus. The generation of these cells is constant and continued to the end of the human life span. T-Cells protects the human body with the use of its distinct self and non-self discrimination ability. In the computer science domain, self/non-self discrimination of the T-Cells are studied and applied in the subject of AIS (Artificial Immune System). A model observed from the HIS while creating these cells, Negative Selection, is added as an algorithm to this subject. The ability to discriminate self from non-self is thought to be useful for the detection of any malicious activity in a computer or a computer network. In this thesis, the Negative Selection Algorithm of the T-Cells is applied in order to detect malicious user input that is submitted from HTTP GET parameters. Detection is done through detectors strings with varying lengths. Detectors are constructed with randomly chosen n-gram strings generated from the training dataset. The number of n-gram strings to form a single detector is determined with the use of Poisson Probability. Detection rates, number of attempts needed for generating a single detector, average detection rates for each detector, the lengths of the detectors and number of detectors that can be generated over a course of time are calculated and presented.

Announcement Category

Muhsin Aldemir : Social Network Analysis of Malicious Websites for Detection and Characterization

Msc. Candidate: Muhsin Aldemir

Program: Information Systems

Date: 02.09.2019 15:30 p.m

Place: A-108

Abstract: Malicious websites pose major risks to users and businesses including economic damages, privacy breaches and loss of valuable data. Malicious actors use websites as a spreading medium for their motives. Analyzing the relationships between malicious websites and comparing them to benign ones can help understand the problem better, and enable detection and prevention of these websites more accurately. This thesis focuses on detection and characterization of malicious websites using Social Network Analysis (SNA). SNA provides powerful methodologies for discovering and visualizing the relationships between actors. By utilizing the links in between and among malicious and benign websites, graphs were constituted, whose nodes were websites and ties were hyperlinks between them. For this purpose, the data which included the snapshot of the pairwise links amongst millions of websites, the list of malicious websites and their types were obtained from the web. First, the same size networks of malicious and benign websites were characterised and compared using their descriptive properties. Then, using these networks new analyses were carried out to determine malicious websites and their types based on their network structures and link similarities. Results were presented showing the detection accuracies of applied methods.

Announcement Category

Ahmet Serhat Demir : A Fully Decentralized Framework for Securely Sharing Digital Contents

Msc. Candidate: Ahmet Serhat Demir

Program: Cyber Security

Date: 04.09.2019 15:00 p.m

Place: A-212

Abstract: Blockchain technology is first known as the secure, immutable, distributed public ledger of the Bitcoin network, which enables value transfer without the need of a trusted third party. Besides cryptocurrencies and finance, blockchain technology has the potential to disrupt several industries, which is made possible with the advance of the smart contracts and decentralized applications. This thesis explores the blockchain technology, Ethereum smart contracts, and investigates the potential of Ethereum Web 3.0 stack for secure information and file sharing in a fully decentralized architecture. It is aimed to discard the need of a central authority in every layer of the application, and cope with the drawbacks of centralized content exchange platforms. Accordingly, a proof-of-concept of a decentralized application is designed. This design is implemented in Ethereum Web 3.0 stack using blockchain for the immutable distributed ledger, Ether for cash transfers, and smart contracts for application logic. Since data storage in blockchain is expensive, Swarm is used for decentralized reliable content storage system. Nevertheless, according to our research, permissionless systems in the Ethereum ecosystem lack necessary data privacy, which causes a risk for secure information exchange. In order to provide a secure way of content exchange, public key encryption is utilized to enable sensitive content delivery without the need of a pre-shared secret. Also, to protect both buyer and seller, a double escrow functionality is implemented. According to the validation and evaluation of our proof-of-concept, we successfully show that Ethereum Web 3.0 stack is applicable for securely sharing digital contents.

Announcement Category

Burak Çelik : OPTIMIZATION OF ADVANCED ENCRYPTION STANDARD (AES) ON CUDA

Msc. Candidate: Burak Çelik

Program: Cyber Security

Date: 04.09.2019 14:00 p.m

Place: A-212

Abstract: This thesis presents several optimization techniques of AES implementations on CUDA. 6 different CUDA kernels are implemented for AES-128 exhaustive search with different software designs and they are compared with each other using Nsight experiment results. Outcome of these results are used for finding the best CUDA implementation and from it, AES-128, AES-192 and AES-256 versions are created for exhaustive search, on the fly CTR and file encryption. They are compared with CPU implementations in order to decide whether GPU or CPU is the fastest considering these topics. For this comparison, two different type of CPU implementations are created which are AES-NI, using new instruction set of Intel, and basic C++. 1, 2, 4 and 8 threads versions of these implementations are compared with CUDA and results are shared. According to them, CUDA is 21, 19 and 18 times faster than the best CPU implementations for exhaustive search with respect to key length. These ratios are 4 times for CTR implementations in which 37.52 GBs of data can be encrypted each second while using CUDA. File encryption for CUDA is 22, 19 and 17 times faster than the best CPU implementations. CUDA can encrypt 31.24 GBs of data per second in this regard without considering I/O operations.

Announcement Category

Nur Didem Başkurt : Omnidirectional Hyperspectral Imaging

PhD. Candidate: Nur Didem Başkurt

Program: Information Systems

Date: 28.08.2019 10:00 a.m

Place: Conference Hall 01

Abstract: We aim to integrate hyperspectral cameras with catadioptric omnidirectional imaging systems to be able to benefit from the advantages of both. Hyperspectral imaging systems provide dense spectral information about the scene being investigated by collecting contiguous data from high number of bands on the electromagnetic spectrum. However the low spatial resolution of these sensors frequently bring about the mixing problem in remote sensing applications. Several unmixing approaches are developed in order to handle the challenging mixing problem on perspective images. On the other hand, omnidirectional imaging systems provide a 360-degree field of view in a single image, while they renounce high spatial resolution. Catadioptric images introduce a radial warping due to the structure of the mirror used in the system. This warping causes a non-uniformity in the spatial resolution which makes the unmixing problem more complicated. In this context, a novel spatial-contextual unmixing algorithm is developed specialized for the large field of view hyperspectral imaging systems. The proposed algorithms are evaluated on various real-world and simulated cases. Experimental results show that the proposed approach outperforms compared methods.

Announcement Category

Pages

Subscribe to RSS - Thesis defense