Bilgisayar Mühendisliği Bölümü yayınlarını içerir. http://hdl.handle.net/20.500.12416/253 2026-10-28T17:21:29Z 2026-10-28T17:21:29Z Abdulkareem, Marwa Issam Ashour, Osama Ibraheem Salman, Yücel Batu http://hdl.handle.net/20.500.12416/8516 2024-10-23T07:22:25Z 2023-01-01T00:00:00Z

Secure IoT Entrance Using Mobile Application Abdulkareem, Marwa Issam; Ashour, Osama Ibraheem; Salman, Yücel Batu The impact of cyber security attacks increased globally, implementing proper security standards to protect data in the cyber environment has been prioritized, while assets are also at risk of being exploited through physical security breaches. Considering the potential risk of Radio Frequency Identification (RFID) cards being lost or stolen, third parties can effortlessly gain the privileges of an authorized person. In this paper, we propose a design for a secure access control system that operates on an Android phone with multi-factor authentication to enable secure access control systems. For this purpose, the authorized users are registered in a database that can be accessed by the access control system when the user authenticates his\her credentials with a login/password as well as biometric data from his\her smartphone. This system works when the user is 10 meters away from the access control system, after that the user will be asked to submit his\her biometric credentials. The database then compares the user's keys and grants access if authentication is successful. This design is intended to reduce the number of cases in which unauthorized access to a restricted area. The observed results clearly meet the required security of physical access control systems.

2023-01-01T00:00:00Z Saran, Ayse Nurdan http://hdl.handle.net/20.500.12416/8503 2024-07-04T10:05:31Z 2024-01-01T00:00:00Z

On time-memory trade-offs for password hashing schemes Saran, Ayse Nurdan A password hashing algorithm is a cryptographic method that transforms passwords into a secure and irreversible format. It is used not only for authentication purposes but also for key derivation mechanisms. The primary purpose of password hashing is to enhance the security of user credentials by preventing the exposure of plaintext passwords in the event of a data breach. As a key derivation function, password hashing aims to derive secret keys from a master key, password, or passphrase using a pseudorandom function. This review focuses on the design and analysis of time-memory trade-off (TMTO) attacks on recent password hashing algorithms. This review presents a comprehensive survey of TMTO attacks and recent studies on password hashing for authentication by examining the literature. The study provides valuable insights and strategies for safely navigating transitions, emphasizing the importance of a systematic approach and thorough testing to mitigate risk. The purpose of this paper is to provide guidance to developers and administrators on how to update cryptographic practices in response to evolving security standards and threats.

2024-01-01T00:00:00Z Arslan, Serdar http://hdl.handle.net/20.500.12416/8424 2024-05-28T13:28:20Z 2024-05-01T00:00:00Z

Application of BiLSTM-CRF model with different embeddings for product name extraction in unstructured Turkish text Arslan, Serdar Named entity recognition (NER) plays a pivotal role in Natural Language Processing by identifying and classifying entities within textual data. While NER methodologies have seen significant advancements, driven by pretrained word embeddings and deep neural networks, the majority of these studies have focused on text with well-defined grammar and structure. A significant research gap exists concerning NER in informal or unstructured text, where traditional grammar rules and sentence structure are absent. This research addresses this crucial gap by focusing on the detection of product names within unstructured Turkish text. To accomplish this, we propose a deep learning-based NER model which combines a Bidirectional Long Short-Term Memory (BiLSTM) architecture with a Conditional Random Field (CRF) layer, further enhanced by FastText embeddings. To comprehensively evaluate and compare our model’s performance, we explore different embedding approaches, including Word2Vec and Glove, in conjunction with the Bidirectional Long Short-Term Memory and Conditional Random Field (BiLSTM-CRF) model. Furthermore, we conduct comparisons against BERT to assess the efficacy of our approach. Our experimentation utilizes a Turkish e-commerce dataset gathered from the internet, where traditional grammatical and structural rules may not apply. The BiLSTM-CRF model with FastText embeddings achieved an F1 score value of 57.40%, a precision value of 55.78%, and a recall value of 59.12%. These results indicate promising performance in outperforming other baseline techniques. This research contributes to the field of NER by addressing the unique challenges posed by unstructured Turkish text and opens avenues for improved entity recognition in informal language settings, with potential applications across various domains.

2024-05-01T00:00:00Z Dündar, Naz Keçeli, Ali Seydi Kaya, Aydın Sever, Hayri http://hdl.handle.net/20.500.12416/8405 2024-05-27T11:54:29Z 2024-06-01T00:00:00Z

A shallow 3D convolutional neural network for violence detection in videos Dündar, Naz; Keçeli, Ali Seydi; Kaya, Aydın; Sever, Hayri With the recent worldwide statistical rise in the amount of public violence, automated violence detection in surveillance cameras has become a matter of high importance. This work introduces an end-to-end, trainable 3D Convolutional Neural Network (3D CNN) for detecting violence in video footage. The proposed network is inherently capable of processing both spatial and temporal information, thereby obviating the need for additional models that would introduce higher computational requirements and complexity. This work has two main contributions: 1) developing a lightweight 3D CNN suitable for inference on edge devices as mobile systems, and 2) a comprehensive explanation of all components comprising a CNN model, thereby enhances model interpretability. Experiments were conducted to assess the performance of the proposed model using a consolidated dataset combining four benchmark datasets. The results of the experiments support the asserted contributions, which are discussed in detail.

2024-06-01T00:00:00Z