Antti Honkela
LightNews LightNews
ahonkela.bsky.social
Antti Honkela
@ahonkela.bsky.social
830 followers 140 following 7 posts

Prof of machine learning at University of Helsinki. Interested in (differential) privacy and open source software.

Videos
Computer science 46%
Biology 34%
Posts Replies Media Videos

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · 12d
Interesting "Truly private AI" that seems like the first to deliver that, up to what current technology enables.

(Yes, you have to trust the opaque magic of Trusted Execution Environments, but it is hard to see how to realistically avoid that for now.)

confer.to
Confer
Confer - Private AI
confer.to

Reposted by Antti Honkela

ellis.eu
ELLIS @ellis.eu · 14d
📣 Call for posters for @elsa-ai.eu TrustworthyAI4Health Workshop co-located w/ @embl.org AI & Biology Conference, on topics that advance reliable, clinically aligned AI systems across diverse data modalities and healthcare environments.

📅 Mar 9
📍 Heidelberg 🇩🇪
🔗 https://bit.ly/4pEK3OK

#EESAIBio

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · 15d
ELLIS Institute Finland
@ellisinstitute.fi
has an open call for postdocs (DL 9 Feb) www.ellisinstitute.fi/postdoc-recr...

There are 45 PIs with different topics to choose from, including privacy in machine learning with me!
Postdoc positions at ELLIS Institute Finland | ELLIS Institute Finland
Call for postdoctoral researchers in artificial intelligence and machine learning
www.ellisinstitute.fi

Reposted by Antti Honkela

ellisinstitute.fi
ELLIS Institute Finland @ellisinstitute.fi · Dec 12
1 month until deadline! Join us to build your own lab in AI + machine learning research. World-class resources incl. @lumi-supercomputer.eu, generous starting package & professorship affiliation with a university in the world’s happiest country! ➡️ www.ellisinstitute.fi/PI-recruit-2...
#hiring
Text: We're hiring! Principal Investigators in artificial intelligence and machine learning research. Below: ELLIS Institute Finland logo

Reposted by Antti Honkela

elsa-ai.eu
ELSA – European Lighthouse on Secure and Safe AI @elsa-ai.eu · Dec 10
ELSA Board member @ahonkela.bsky.social contributed to the paper"Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning",presented at @neuripsconf.bsky.social'25

Article ➡️ www.helsinki.fi/en/faculty-s...

#MachineLearning #DifferentialPrivacy #PrivacyGuarantees
How to ensure anonymity of AI systems? | Faculty of Science | University of Helsinki
When training artificial intelligence systems, developers need to use privacy-enhancing technologies to ensure that the subjects of the training data are not exposed, new study suggests.
www.helsinki.fi

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · Sep 11
@iclr-conf.bsky.social regarding your LLM policy, can you please confirm that one does not need to have an LLM usage section in the main body of the paper if LLMs did not play a significant role as defined here?
Extract of ICLR LLM use policy with the following text highlighted: "However, new this year, if LLMs played a significant role in research ideation and/or writing to the extent that they could be regarded as a contributor, then authors should describe the precise role of the LLM in the main body of the paper in a separate section on LLM usage."

Reposted by Antti Honkela

elsa-ai.eu
ELSA – European Lighthouse on Secure and Safe AI @elsa-ai.eu · Aug 1
Happy to share the recap of the #health #privacy #session at #CAMDA2025 by our amazing team!

elsa-ai.eu/the-health-p...

#ELSAAI #research #challenge #safeandsecure #AI

Reposted by Antti Honkela

dppapers.bsky.social
Differential Privacy Papers @dppapers.bsky.social · Mar 17
$( varepsilon, δ)$ Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees
Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela
http://arxiv.org/abs/2503.10945
$( varepsilon, δ)$ Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela http://arxiv.org/abs/2503.10945 Current practices for reporting the level of differential privacy (DP) guarantees for machine learning (ML) algorithms provide an incomplete and potentially misleading picture of the guarantees and make it difficult to compare privacy levels across different settings. We argue for using Gaussian differential privacy (GDP) as the primary means of communicating DP guarantees in ML, with the full privacy profile as a secondary option in case GDP is too inaccurate. Unlike other widely used alternatives, GDP has only one parameter, which ensures easy comparability of guarantees, and it can accurately capture the full privacy profile of many important ML applications. To support our claims, we investigate the privacy profiles of state-of-the-art DP large-scale image classification, and the TopDown algorithm for the U.S. Decennial Census, observing that GDP fits the profiles remarkably well in all three cases. Although GDP is ideal for reporting the final guarantees, other formalisms (e.g., privacy loss random variables) are needed for accurate privacy accounting. We show that such intermediate representations can be efficiently converted to GDP with minimal loss in tightness.

Reposted by Antti Honkela

steglelab.bsky.social
Stegle Lab @steglelab.bsky.social · Feb 27
⏰ A quick reminder that Track I of the Health Privacy Challenge is still running strong, exploring privacy preservation in bulk RNA-seq datasets! We’re excited to see the innovative solutions Blue Teams and Red Teams will bring to the competition! #🫐🍅 #CAMDAConference #ISMB/ECCB2025

Reposted by Antti Honkela

steglelab.bsky.social
Stegle Lab @steglelab.bsky.social · Feb 27
Exciting News! 🚀 We’re pleased to launch Track II of the Health Privacy Challenge 🫐🍅, focused on single-cell data! We invite the participants to explore the privacy and utility of synthetic single-cell RNA-seq data! #CAMDAConference
Register to participate: benchmarks.elsa-ai.eu?ch=4
Overview - Health - ELSA Benchmarks Platform
benchmarks.elsa-ai.eu

Reposted by Antti Honkela

ellisinstitute.fi
ELLIS Institute Finland @ellisinstitute.fi · Feb 24
Call for Principal Investigators in #machinelearning & #artificialintelligence closes in 2 weeks! Why apply?
- Professorship affiliation at universities in Finland
- Research infrastructure incl. @lumi-supercomputer.eu
- Generous startup package
- @ellis.eu network
➡️ www.ellisinstitute.fi/PI-recruit
Principal Investigator positions at ELLIS Institute Finland | ELLIS Institute Finland
Now recruiting new PIs in artificial intelligence and machine learning
www.ellisinstitute.fi

Reposted by Antti Honkela

samikaski.bsky.social
Samuel Kaski @samikaski.bsky.social · Feb 4
I have big news: @ellis.eu has launched its 2nd major research center, @ellisfinland.bsky.social! I have agreed to start as founding director & the first call for PI positions is open. This is a major opportunity for outstanding researchers, join us! ellisinstitute.fi/PI-recruit
Principal Investigator positions at ELLIS Institute Finland | ELLIS Institute Finland
Now recruiting new PIs in artificial intelligence and machine learning
ellisinstitute.fi

Reposted by Antti Honkela

lacerbi.bsky.social
Luigi Acerbi @lacerbi.bsky.social · Jan 28
1/ 🎉 We launched the *Helsinki Probabilistic Machine Learning Lab*, which combines multiple research groups at @univhelsinkics.bsky.social - and part of FCAI and ELLIS - working on, guess what, Probabilistic ML and AI.

And we are hiring! Please repost!

Website: www.helsinki.fi/probabilisti...
Helsinki Probabilistic Machine Learning Lab

Reposted by Antti Honkela

icthiit.bsky.social
Helsinki Institute for Information Technology @icthiit.bsky.social · Jan 21
We are now accepting applications for Postdoctoral Fellows (3 years) or Research Fellows (5 years) in ICT. Deadline 2 February at 11:59 PM Finnish time
Find out more information @ shorturl.at/uMk4i #postdocjob #postdoc #artificialintelligence #datascience #bioinformatics #algorithms #AcademicSky
HIIT Postdoctoral and Research Fellow positions
Apply now HIIT Research Fellow and Postdoctoral Fellow Positions in ICT The Helsinki Institute for Information Technology (HIIT) invites applications for Postdoctoral Fellows and Research Fellows. HI...
shorturl.at

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · Jan 15
Very interesting challenge on privacy of synthetic data organised together with @steglelab.bsky.social and other ELSA project partners.

Please spread the word!
steglelab.bsky.social Stegle Lab @steglelab.bsky.social · Jan 15
We are delighted to announce The Health Privacy Challenge, an interactive opportunity for advancement at the intersection of computational biology and privacy research, brought to you as a part of CAMDA Conference at #ISMB/ECCB2025 🫐🍅
Register to participate: benchmarks.elsa-ai.eu?ch=4
Overview - Health - ELSA Benchmarks Platform
benchmarks.elsa-ai.eu

Reposted by Antti Honkela

steglelab.bsky.social
Stegle Lab @steglelab.bsky.social · Jan 15
We are delighted to announce The Health Privacy Challenge, an interactive opportunity for advancement at the intersection of computational biology and privacy research, brought to you as a part of CAMDA Conference at #ISMB/ECCB2025 🫐🍅
Register to participate: benchmarks.elsa-ai.eu?ch=4
Overview - Health - ELSA Benchmarks Platform
benchmarks.elsa-ai.eu

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · Dec 14
This would be rather suboptimal for those living further away from big centers or working in an area where most of the relevant community is elsewhere. Unfortunately we need common meetings to avoid fragmenting the community.

Reposted by Antti Honkela

maosbot.bsky.social
M A Osborne @maosbot.bsky.social · Nov 24
I have seen some anti-peer-review takes on here, and, believe me, I understand the frustrations, but I would urge caution before doing or publicly saying anything too drastic. We live in age rife with misinformation and anti-intellectualism—not everyone wants academia to survive

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · Nov 26
Risk is twofold: 1) Europeans risk losing access to models developed outside Europe, while 2) European researchers face significant additional burden to comply with the rules. This risks violating the freedom of research.

ahonkela.bsky.social
Antti Honkela @ahonkela.bsky.social · Nov 26
Open letter: European AI researchers are worried that including research and open source in foundation model regulation in the AI Act could kill frontier AI research in Europe. docs.google.com/document/d/1...
Open Letter on Regulation of Foundation Models in the AI Act and Research
Open Letter on Regulation of Foundation Models in the AI Act and Research If you are a machine learning or AI researcher with at least a PhD and wish to sign the letter, please fill in this form: http...
docs.google.com