Ege Erdogan

According to our database, Ege Erdogan authored at least 12 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing.

Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan, Florian Matthes, Gjergji Kasneci

CoRR, August, 2025

Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study.

Mahdi Dhaini, Juraj Vladika, Ege Erdogan, Zineb Attaoui, Gjergji Kasneci

CoRR, August, 2025

Geometric Flow Models over Neural Network Weights.

Ege Erdogan

CoRR, April, 2025

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods.

Mahdi Dhaini, Ege Erdogan, Nils Feldhus, Gjergji Kasneci

Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025

2024

Explainability Meets Text Summarization: A Survey.

Mahdi Dhaini, Ege Erdogan, Smarth Bakshi, Gjergji Kasneci

Proceedings of the 17th International Natural Language Generation Conference, 2024

SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection.

Ege Erdogan, Unat Teksen, Mehmet Salih Celiktenyildiz, Alptekin Küpçü, A. Ercüment Çiçek

Proceedings of the Cryptology and Network Security - 23rd International Conference, 2024

2023

Poisoning × Evasion: Symbiotic Adversarial Robustness for Graph Neural Networks.

Ege Erdogan, Simon Geisler, Stephan Günnemann

CoRR, 2023

Detecting ChatGPT: A Survey of the State of Detecting ChatGPT-Generated Text.

Mahdi Dhaini, Wessel Poelman, Ege Erdogan

CoRR, 2023

Defense Mechanisms Against Training-Hijacking Attacks in Split Learning.

Ege Erdogan, Unat Teksen, Mehmet Salih Celiktenyildiz, Alptekin Küpçü, A. Ercüment Çiçek

CoRR, 2023

2021

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

Ege Erdogan, Alptekin Küpçü, A. Ercüment Çiçek

IACR Cryptol. ePrint Arch., 2021

UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning.

Ege Erdogan, Alptekin Küpçü, A. Ercüment Çiçek

IACR Cryptol. ePrint Arch., 2021

Demo - Zelig: Customizable Blockchain Simulator.

Ege Erdogan, Can Arda Aydin, Öznur Özkasap, Waris Gill

CoRR, 2021