Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
Future Blog Post for Course Notes
Published:
I will share my lecture notes here soon! If you want to help to check my course notes, hit me up!
projects
Instagram Follower & Following List Scraper Permalink
Published:
Creates a list of followers and following with the current time. Repo
Academics Blog Content Management System Permalink
Published:
Content Management System for scholars. Easy-to-use admin panel and easy to understand theme. Feel free to contribute! Repo
ML Projects from Scratch Permalink
Published:
Here I collect some basic ML, NN models that I wrote from scratch to learn how they works. Some of them are repetitions of codes already written in the tutorials, with new comments and code simplifications made on them. For credits, see below: Github Repo
SplitOut: Code Repository of Paper Permalink
Published:
Split learning enables efficient and privacy-aware training of a deep neural network by splitting a neural network so that the clients (data holders) compute the first layers and only share the intermediate output with the central compute-heavy server. This paradigm introduces a new attack medium in which the server has full control over what the client models learn, which has already been exploited to infer the private data of clients and to implement backdoors in the client models. Although previous work has shown that clients can successfully detect such training-hijacking attacks, the proposed methods rely on heuristics, require tuning of many hyperparameters, and do not fully utilize the clients’ capabilities. In this work, we show that given modest assumptions regarding the clients’ compute capabilities, an out-of-the-box outlier detection method can be used to detect existing training-hijacking attacks with almost-zero false positive rates. We conclude through experiments on different tasks that the simplicity of our approach we name SplitOut makes it a more viable and reliable alternative compared to the earlier detection methods.
JWT CRUD Social Media Platform for TurkishNLP Community Permalink
Published:
Topic Modeling for Bloomberg Quint News Dataset. Live plots and coherence score & perplexity metrics are also included! Backend Repo Frontend Repo
LDA Topic Modeling for Bloomberg News Permalink
Published:
Topic Modeling for Bloomberg Quint News Dataset. Live plots and coherence score & perplexity metrics are also included! Repo
Title Generator with LLM & PEFT (LoRA) Permalink
Published:
Topic Modeling for Bloomberg Quint News Dataset. Live plots and coherence score & perplexity metrics are also included! Repo
dynbatcher - Dynamic Batch Size Dataloader Generator Permalink
Published:
dynbatcher is a Python package designed to facilitate the creation and management of PyTorch DataLoaders with custom batch sizes and ratios. This package is especially useful for training neural networks with dynamic batch sizes. With dynbatcher you can divide a dataset into subsets with different batch sizes and turn it into a single Dataloader ready for training. Github Repo PyPI
publications
Defense Mechanisms Against Training-Hijacking Attacks in Split Learning
Published in arXiv, 2023
Recommended citation: E. Erdogan, U. Teksen, M. S. Celiktenyildiz, A. Kupcu, ve A. E. Cicek, “Defense Mechanisms Against Training-Hijacking Attacks in Split Learning”. arXiv, 16 February 2023. [Online]. http://arxiv.org/abs/2302.08618v1
SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
Published in arXiv (under review for a conference), 2023
Recommended citation: E. Erdogan, U. Teksen, M. S. Celiktenyildiz, A. Kupcu, ve A. E. Cicek, “SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection”. arXiv, 11 December 2023. [Online]. http://arxiv.org/abs/2302.08618
research
Motivating Children to Develop New Technologies through Human-Computer Interaction Scenes on Movies, and Understanding Technology Based on Human Limitations
Published:
This paper is one of the assignments of Human-Computer Interaction Course (CMPE476) to analyze the relationship between Human-Computer Interaction(HCI) technologies with education in the limitations of humanity.
On the Limitations of Assistive Human-Computer Interaction Technologies: Why Should We Have Them and How to Determine Them?
Published:
This paper is one of the assignments of Human-Computer Interaction Course (CMPE476) to determine the thresholds for HCI research and developing assistive systems.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.