Leyla Naz Candogan

Research Interests:

  • Adversarial Machine Learning
  • Robustness

 

Biography

I received my Bachelor’s degree with a double major in Electrical-Electronics Engineering and Physics from Bilkent University, Turkey in June 2023. After that, I started my Ph.D. in the Laboratory for Information and Inference Systems of EPFL in September 2023.

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

L. Candogan; A. Afzal; P. Puigdemont; V. Cevher 

2026. 43rd International Conference on Machine Learning (ICML 2026), Seoul, South Korea, 2026-07-06 – 2026-07-11.

Detailed record

Linear Attention for Efficient Bidirectional Sequence Modeling

A. Afzal; E. Abad Rocamora; L. Candogan; P. Puigdemont; F. Tonin et al. 

2025. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025-12-02 – 2025-12-07.

Detailed record

Quantum-Peft: Ultra Parameter-Efficient Fine-Tuning

T. Koike-Akino; F. Tonin; Y. Wu; F. Z. Wu; L. Candogan et al. 

2025. The Thirteenth International Conference on Learning Representations, Singapore, 2025-04-24-2025-04-28.

Detailed record

Single-pass Detection of Jailbreaking Input in Large Language Models

L. Candogan; Y. Wu; E. Abad Rocamora; G. Chrysos; V. Cevher 

Transactions on Machine Learning Research. 2025. Vol. 02/2025.

Detailed record

Contact

e-mail address: Leyla Naz Candogan

EPFL people page

Access map