Igor Shilov (➡️ ICML 🇨🇦)
@igorshilov.bsky.social
Anthropic AI Safety Fellow
PhD student at Imperial College London.
ML, interpretability, privacy, and stuff
🏳️🌈
https://igorshilov.com/
PhD student at Imperial College London.
ML, interpretability, privacy, and stuff
🏳️🌈
https://igorshilov.com/
Arrived in beautiful Vancouver!
More conferences with mountain views please!
Ping me if you want to chat about privacy and security of LLMs!
More conferences with mountain views please!
Ping me if you want to chat about privacy and security of LLMs!
July 16, 2025 at 1:43 PM
Arrived in beautiful Vancouver!
More conferences with mountain views please!
Ping me if you want to chat about privacy and security of LLMs!
More conferences with mountain views please!
Ping me if you want to chat about privacy and security of LLMs!
New paper accepted @ USENIX Security 2025!
We show how to identify training samples most vulnerable to membership inference attacks - FOR FREE, using artifacts naturally available during training! No shadow models needed.
Learn more: computationalprivacy.github.io/loss_traces/
Thread below 🧵
We show how to identify training samples most vulnerable to membership inference attacks - FOR FREE, using artifacts naturally available during training! No shadow models needed.
Learn more: computationalprivacy.github.io/loss_traces/
Thread below 🧵
Loss Traces: Free Privacy Risk Evaluation
Estimate the vulnerability of training samples to membership inference attacks by analyzing their loss traces during model training - no shadow models required!
computationalprivacy.github.io
June 24, 2025 at 3:17 PM
New paper accepted @ USENIX Security 2025!
We show how to identify training samples most vulnerable to membership inference attacks - FOR FREE, using artifacts naturally available during training! No shadow models needed.
Learn more: computationalprivacy.github.io/loss_traces/
Thread below 🧵
We show how to identify training samples most vulnerable to membership inference attacks - FOR FREE, using artifacts naturally available during training! No shadow models needed.
Learn more: computationalprivacy.github.io/loss_traces/
Thread below 🧵
Reposted by Igor Shilov (➡️ ICML 🇨🇦)
Check out our new pre-print "Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models", joint work with fantastic colleagues from Google (DeepMind) and many other great institutions! Find it here: arxiv.org/abs/2505.18773
Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a resu...
arxiv.org
May 27, 2025 at 8:00 AM
Check out our new pre-print "Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models", joint work with fantastic colleagues from Google (DeepMind) and many other great institutions! Find it here: arxiv.org/abs/2505.18773
Mom I'm on TV
🏆 And the Best Paper Award at #SaTML25 goes to “SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)” by Matthieu Meeus, Igor Shilov, Shubham Jain, Manuel Faysse, Marek Rei, Yves-Alexandre de Montjoye. Well deserved!
April 9, 2025 at 8:48 AM
Mom I'm on TV
📢 Privacy in ML Meetup @ Imperial is back!
📅 February 4th, 6pm, Imperial College London
We are happy to announce the new date for the first Privacy in ML Meetup @ Imperial, bringing together researchers from across academia and industry.
RSVP: www.imperial.ac.uk/events/18318...
📅 February 4th, 6pm, Imperial College London
We are happy to announce the new date for the first Privacy in ML Meetup @ Imperial, bringing together researchers from across academia and industry.
RSVP: www.imperial.ac.uk/events/18318...
Privacy in Machine Learning Meetup @ Imperial
The Computational Privacy Group at Imperial College London is organizing the first Machine Learning Privacy meetup, recognizing the growing community of researchers in and around London working at the...
www.imperial.ac.uk
December 17, 2024 at 10:26 AM
📢 Privacy in ML Meetup @ Imperial is back!
📅 February 4th, 6pm, Imperial College London
We are happy to announce the new date for the first Privacy in ML Meetup @ Imperial, bringing together researchers from across academia and industry.
RSVP: www.imperial.ac.uk/events/18318...
📅 February 4th, 6pm, Imperial College London
We are happy to announce the new date for the first Privacy in ML Meetup @ Imperial, bringing together researchers from across academia and industry.
RSVP: www.imperial.ac.uk/events/18318...
Reposted by Igor Shilov (➡️ ICML 🇨🇦)
So easy to be cynical and glib. No-one is under any illusions about the way events often play out in the Middle East, or the character of the groups who defeated Assad. But it is ok to hope. It is ok to celebrate the end of a dictator.
December 8, 2024 at 11:49 AM
So easy to be cynical and glib. No-one is under any illusions about the way events often play out in the Middle East, or the character of the groups who defeated Assad. But it is ok to hope. It is ok to celebrate the end of a dictator.
Sophon was such an overkill for halting Earth's research. All Trisolarans needed to do was to destroy Overleaf - with the exact same outcome.
December 3, 2024 at 3:30 PM
Sophon was such an overkill for halting Earth's research. All Trisolarans needed to do was to destroy Overleaf - with the exact same outcome.
Wow so we actually got to a point where Anthropic sponsors exhibitions at Tate modern
November 20, 2024 at 11:06 AM
Wow so we actually got to a point where Anthropic sponsors exhibitions at Tate modern
Surprising fact of the day: Gordon Brown is a Scot
January 18, 2024 at 7:34 PM
Surprising fact of the day: Gordon Brown is a Scot
Low-stakes conspiracy of the day: the protestor throwing glitter at Starmer was a personal favour from Starmer himself. Because as a serious politician you don’t get to wear glitter in public anymore, and sometimes nothing hits quite like it
October 13, 2023 at 9:28 AM
Low-stakes conspiracy of the day: the protestor throwing glitter at Starmer was a personal favour from Starmer himself. Because as a serious politician you don’t get to wear glitter in public anymore, and sometimes nothing hits quite like it
Почему существует prediction market на задержки рейсов и почему у него есть деньги на рекламу в твиттере
app.wingman.wtf/hot-flights
app.wingman.wtf/hot-flights
September 20, 2023 at 6:46 PM
Почему существует prediction market на задержки рейсов и почему у него есть деньги на рекламу в твиттере
app.wingman.wtf/hot-flights
app.wingman.wtf/hot-flights