Portfolio

2023-07-18 - Lecture at the ARTISAN summer school Towards Machine Learning Models that We Can Trust: Hacking and (properly) Testing AI .

Published: July 18, 2023

2022-06-22 - Poster presentation at ICML Workshop Shift happens: Crowdsourcing metrics and test datasets beyond ImageNet, for the paper ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches .

Published: June 22, 2022

2022-02-18 - PhD Thesis .

Published: February 18, 2022

2021-12-07 - Poster presentation at NeurIPS, for the paper Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints .

Published: December 07, 2021

2021-11-10 - Pandavision .

Published: November 10, 2021

2021-07-24 - Poster presentation at Cybersec&AI, for the paper Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples .

Published: November 05, 2021

2021-10-26 Presentation: ML Explainability Techniques .

Published: October 26, 2021

2021-07-24 - Poster presentation at ICML Workshop A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning, for the paper Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples .

Published: July 24, 2021

2021-07-24 - Oral presentation at ICML Workshop A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning, for the paper Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints .

Published: July 24, 2021

2020-11-04 - Tutorial: Image Classification Web Server - Industrial Software Development course .

Published: November 04, 2020

2019-12-11 - Web Servers - Industrial Software Development course .

Published: December 11, 2019

2019-10-25 - Cybersec&AI Prague .

Published: October 25, 2019

2019-08-06 - Secml Library .

Published: August 06, 2019