Ege Erdogan

MSc Informatics at the Technical University of Munich

Hey! I am Ege, currently in my first year of the Informatics MSc program at TUM. I am broadly interested in machine (nowadays read deep) learning and issues around how we should or should not use ML systems, such as data privacy, safety, and explainability.

While I was an undergrad (CS & Math) at Koç University in Istanbul, Turkey, I worked as a research intern at the Cryptography, Security, and Privacy Research Group on various projects related to data privacy in collaborative ML (more on them here and here).

My putative long-term goal is to a obtain a PhD in computer science, working more deeply on the topics above.

I really don’t think you are curious how I spend my free time or who my favorite composer is and why, so I will skip that part. Feel free to contact me at ege at erdogan.dev.

news

Feb 2023	📖 Starting the Intro to ML Safety course organized by the Center for AI Safety.
Oct 2022	📖 Starting the Informatics MSc program at TUM.
Sep 2022	🎉 UnSplit and SplitGuard accepted for presentation at WPES ‘22 organized as part of ACM CCS.
Jun 2022	Graduated from Koç University with BS degrees in computer engineering and mathematics.

selected publications

WPES 2022

SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning

Erdogan, Ege, Kupcu, Alptekin, and Cicek, A Ercument

The 21st Workshop on Privacy in the Electronic Society 2022

Bib Website

@article{erdogan2021splitguard,
  title = {SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning},
  author = {Erdogan, Ege and Kupcu, Alptekin and Cicek, A Ercument},
  journal = {The 21st Workshop on Privacy in the Electronic Society},
  year = {2022},
}

WPES 2022

UnSplit: Data-oblivious model inversion, model stealing, and label inference attacks against split learning

Erdogan, Ege, Kupcu, Alptekin, and Cicek, A Ercument

The 21st Workshop on Privacy in the Electronic Society 2022

Bib Website

@article{erdogan2021unsplit,
  title = {UnSplit: Data-oblivious model inversion, model stealing, and label inference attacks against split learning},
  author = {Erdogan, Ege and Kupcu, Alptekin and Cicek, A Ercument},
  journal = {The 21st Workshop on Privacy in the Electronic Society},
  year = {2022},
}

SRDS 2021

(Demo) Zelig: Customizable Blockchain Simulator

Erdogan, Ege, Aydin, Can Arda, Ozkasap, Oznur, and Gill, Waris

40th International Symposium on Reliable Distributed Systems 2021

arXiv Bib

@article{erdogan2021zelig,
  title = {(Demo) Zelig: Customizable Blockchain Simulator},
  author = {Erdogan, Ege and Aydin, Can Arda and Ozkasap, Oznur and Gill, Waris},
  journal = {40th International Symposium on Reliable Distributed Systems},
  year = {2021},
}