Joonas Jälkö

Postdoc, University of Helsinki

Joined

March 2017

Names

Joonas Jälkö

Emails

****@helsinki.fi (Confirmed)

****@aalto.fi (Confirmed)

Personal Links

DBLP

Career & Education History

Postdoc

University of Helsinki (helsinki.fi)

2023 – Present

PhD student

Aalto University (aalto.fi)

2018 – 2023

MS student

University of Helsinki (helsinki.fi)

2011 – 2017

Advisors, Relations & Conflicts

Postdoc Advisor

Antti Honkela

2023 – Present

PhD Advisor

Samuel Kaski

2018 – 2023

Expertise

differential privacy

bayesian inference

variational inference

Present

Publications

Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
Gauri Pradhan, Joonas Jälkö, Santiago Zanella-Beguelin, Antti Honkela
- ICLR 2026 Poster
- Readers: Everyone
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Marlon Tobaben, Hibiki Ito, Joonas Jälkö, Yuan He, Antti Honkela
- NeurIPS 2025 poster
- Readers: Everyone
Towards Efficient and Scalable Implementation of Differentially Private Deep Learning
Sebastian Rodriguez Beltran, Marlon Tobaben, Joonas Jälkö, Niki Andreas Loppi, Antti Honkela
- Submitted to ICML 2025
- Readers: Everyone
NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie JOSEPH, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota et al. (7 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Privacy-aware document visual question answering
Rubèn Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, Joonas Jälkö, Vincent Poulain d'Andecy, Aurélie JOSEPH, Lei Kang, Ernest Valveny, Antti Honkela, Mario Fritz, Dimosthenis Karatzas
- ICDAR 2024
- Readers: Everyone
Noise-Aware Differentially Private Variational Inference
Talal Alrawajfeh, Joonas Jälkö, Antti Honkela
- AISTATS 2025 Poster
- Readers: Everyone
Towards Efficient and Scalable Implementation of Differentially Private Deep Learning
Sebastian Rodriguez Beltran, Marlon Tobaben, Joonas Jälkö, Niki Andreas Loppi, Antti Honkela
- Submitted to ICLR 2025
- Readers: Everyone
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Marlon Tobaben, Hibiki Ito, Joonas Jälkö, Gauri Pradhan, Yuan He, Antti Honkela
- Submitted to ICLR 2025
- Readers: Everyone
NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito, Khanh Nguyen, Raouf Kerkouche, Kangsoo Jung, Joonas Jälkö, Lei Kang, Andrey Barsky, Vincent Poulain d'Andecy, Aurélie JOSEPH, Aashiq Muhamed, Kevin Kuo, Virginia Smith, Yusuke Yamasaki, Takumi Fukami, Kenta Niwa, Iifan Tyou, Hiro Ishii, Rio Yokota et al. (7 additional authors not shown)
- Submitted to NeurIPS 2024 Track Datasets and Benchmarks
- Readers: Everyone
Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation
Ossi Räisä, Joonas Jälkö, Antti Honkela
- PML
- Readers: Everyone

View all 23 publications

Co-Authors

View all 44 co-authors