Shpresim Sadiku
I am interested in the theory and applications of 2D Computer Vision and Optimization. Currently, I am using first-order optimization methods to generate sparse adversarial attacks of high visual quality.
๐ฌ Contact
- office
- Room 3027 at ZIB
- sadiku (at) zib.de
- homepage
- shpresimsadiku.com
- languages
- Albanian, English, German, and Serbian
๐ Curriculum vitae
- since 2020
- Researcher at ZIB
- since 2020
- Member of BMS
- May 2020
- M.Sc. in Mathematics in Data Science at Technical University of Munich
- Jul 2017
- B.Sc. in Mathematics at University of Tirana
๐ Publications and preprints
Preprints
๐ฌ Talks and posters
Conference and workshop talks
- Sep 2022
- Wavelet-based Low Frequency Adversarial Attacks
3rd BMS-BGSMath Junior Meeting, Barcelona [PDF] - Mar 2021
- Neural Network Approximation Theory
BMS Conference [PDF]
Research seminar talks
- Aug 2023
- Minimally Distorted Explainable Adversarial Attacks
AIP Seminar, RIKEN Center for Advanced Intelligence Project, Tokyo - Feb 2023
- What Is Backpropagation?
"What is ...?" seminar [PDF]
Poster presentations
- Mar 2024
- Group-wise Sparse and Explainable Adversarial Attacks
Deep Learning: Theory, Applications, and Implications, RIKEN Center for Advanced Intelligence Project, Tokyo - Mar 2023
- Wavelet-based Low Frequency Adversarial Attacks
Workshop on Optimization and Machine Learning, Waischenfeld
๐จโ๐ซ Teaching
- summer 2019
- Tutor for Computational Statistics at Technical University of Munich
๐ Organization and outreach
- 2022
- Assisted in the organization of the IOL-DISCOGA Seminar in Berlin