arXiv subjects

Zeynep Özdemir

Publications and source records attributed to Zeynep Özdemir.

3 recordsLinked to original sources

arXiv2026

From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News

In this study, we examine how modern LLMs generate and detect fake news under controlled settings across four manipulation scenarios. These are open-ended generation, rewriting, manipulation prompts and attribute based prompts grounded in the journalistic discourse framework. Firstly, using seven widely adapted models, we created a synthetic fake news corpus with 14000 generated articles across these four scenarios. Then we analyzed its linguistic properties to assess how closely model-generated news resembles real news structurally and semantically. Finally, to evaluate detection performance, we conducted experiments where each model judges generated fake news, starting with a basic detection prompt and improved prompts developed through an iterative refinement process that extracts misleading patterns from real-fake pairs. Our results revealed substantial variation across models in both generating and detecting misinformation, demonstrated that the generation strategy strongly influences detectability, and show that the refined prompt does not improve and often harms detection performance. Therefore, the study provides a systematic assessment of LLMs detection capability of LLMs generated fake news across typical generation scenarios.

cs.CL↗

arXiv2025

Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution

Building accurate models for rare skin diseases remains challenging due to the lack of sufficient labeled data and the inherently long-tailed distribution of available samples. These issues are further complicated by inconsistencies in how datasets are collected and their varying objectives. To address these challenges, we compare three learning strategies: episodic learning, supervised transfer learning, and contrastive self-supervised pretraining, within a few-shot learning framework. We evaluate five training setups on three benchmark datasets: ISIC2018, Derm7pt, and SD-198. Our findings show that traditional transfer learning approaches, particularly those based on MobileNetV2 and Vision Transformer (ViT) architectures, consistently outperform episodic and self-supervised methods as the number of training examples increases. When combined with batch-level data augmentation techniques such as MixUp, CutMix, and ResizeMix, these models achieve state-of-the-art performance on the SD-198 and Derm7pt datasets, and deliver highly competitive results on ISIC2018. All the source codes related to this work will be made publicly available soon at the provided URL.

cs.CV↗

arXiv2019

Design of Internet of Things Based Controller for Direct Current Motors

It is known that internet have been widespread in many areas of life and enabled machines to communicate each other. The terms of Internet of Things (IoT) has emerged as a result of networks consist of machines and equipment that work independent of operator and communicate each other. Sensors, embedded systems, communication technologies and data storage systems like clouds create wide area networks that can communicate and share data. In this study, the application of the IoT on a low speed mechanical benchmark driven by a direct current motor has been designed. It is aimed to keep the motor speed fixed at desired value according to the changings occurs depending on varying the pressure acting on the actuators. In presented study, a speed control is performed by establishing a modeling and simulation mechanism that will give the closest results to the real system.

cs.RO↗