Nataša Krčo
@natasakrco.bsky.social
PhD student in ML Privacy @ Imperial College
Reposted by Nataša Krčo
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 Nataša Krčo
How do you know your synthetic data is anonymous 🥸?
If your answer is “we checked Distance to Closest Record (DCR),” then… we might have bad news for you.
Our latest work shows DCR and other proxy metrics to be inadequate measures of the privacy risk of synthetic data.
If your answer is “we checked Distance to Closest Record (DCR),” then… we might have bad news for you.
Our latest work shows DCR and other proxy metrics to be inadequate measures of the privacy risk of synthetic data.
May 9, 2025 at 12:21 PM
How do you know your synthetic data is anonymous 🥸?
If your answer is “we checked Distance to Closest Record (DCR),” then… we might have bad news for you.
Our latest work shows DCR and other proxy metrics to be inadequate measures of the privacy risk of synthetic data.
If your answer is “we checked Distance to Closest Record (DCR),” then… we might have bad news for you.
Our latest work shows DCR and other proxy metrics to be inadequate measures of the privacy risk of synthetic data.
Reposted by Nataša Krčo
📢 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...