Brian Pulfer
Hey there, this is Brian! đ
I am a Machine Learning practitioner and enthusiast. I am currently a Ph.D. student in Machine Learning, with a focus on anomaly detection and adversarial attacks, at the University of Geneva, Switzerland đ¨đ. Here's my CV. This is my personal portfolio, where I publish updates on my career, projects, publications and more. Hope you enjoy it!
News đī¸
June 2025
đ¨đŊâđģI am interning a as a Ph.D. student at Meta in Menlo Park, California, for the summer of 2025 in the GPU Techniques Team!
June 2025
đ I presented our paper Task-Agnostic Attacks Against Vision Foundation Models at CVPR 2025 for the 5th Workshop of Adversarial Machine Learning on Computer Vision: Foundation Models + X.
March 2025
đ Our paper Task-Agnostic Attacks Against Vision Foundation Models is now available on ArXiv.
February 2025
đ I contributed as part of the red team for ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models.
November 2024
đĩī¸ I contributed as a reviewer of 3 papers for CVPR 2025.
July 2024
đ Our paper Robustness Tokens: Towards Adversarial Robustness for Transformers (deep double blind) has been accepted for publication at the European Conference on Computer Vision (ECCV) 2024..
September 2023
đĨ My team and I won the Migros workshop at the HackZurich 2023 hackathon. Read the blog post.
September 2023
đ Our work Weather4cast at NeurIPS 2022: Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts has been accepted for publication in Proceedings of Machine Learning Research.
January 2023
đ Our work Model vs System Level Testing of Autonomous Driving Systems: A Replication and Extension Study has been accepted for publication in Empirical Software Engineering.
December 2022
đĨ Our work Solving the Weather4cast Challenge via Visual Transformers for 3D Images got us the third place in the 2022 NeurIPS Weather4cast competition workshop.
August 2022
đ Our work Anomaly localization for copy detection patterns through print estimations was accepted for publication in the IEEE International Workshop on Information Forensics & Security.
June 2022
đ Our work Authentication of Copy Detection Patterns under Machine Learning Attacks: A Supervised Approach was accepted for publication in the 29th IEEE International Conference on Image Processing (ICIP).
May 2022
đĨ I won the best presentation award for the 2022 edition of the SwissEngineering Award Foundation.
December 2021
đ Our work Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems was accepted for publication in the IEEE Transactions of Software Engineering (TSE).
November 2021
đĨ I Joined the Stochastic Information Processing (SIP) group of the University of Geneva in quality of Ph.D. Student in Machine Learning.