Search Results for author: Yves-Alexandre de Montjoye

Found 9 papers, 2 papers with code

Copyright Traps for Large Language Models

no code implementations14 Feb 2024 Matthieu Meeus, Igor Shilov, Manuel Faysse, Yves-Alexandre de Montjoye

We here propose to use copyright traps, the inclusion of fictitious entries in original content, to detect the use of copyrighted materials in LLMs with a focus on models where memorization does not naturally occur.

Memorization

Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models

no code implementations23 Oct 2023 Matthieu Meeus, Shubham Jain, Marek Rei, Yves-Alexandre de Montjoye

First, we propose a procedure for the development and evaluation of document-level membership inference for LLMs by leveraging commonly used data sources for training and the model release date.

Misinformation Sentence

Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data

no code implementations4 Jul 2023 Florent Guépin, Matthieu Meeus, Ana-Maria Cretu, Yves-Alexandre de Montjoye

While membership inference attacks (MIAs), based on shadow modeling, have become the standard to evaluate the privacy of synthetic data, they currently assume the attacker to have access to an auxiliary dataset sampled from a similar distribution as the training dataset.

Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing

no code implementations17 Jun 2023 Matthieu Meeus, Florent Guépin, Ana-Maria Cretu, Yves-Alexandre de Montjoye

The choice of vulnerable records is as important as more accurate MIAs when evaluating the privacy of synthetic data releases, including from a legal perspective.

Re-aligning Shadow Models can Improve White-box Membership Inference Attacks

no code implementations8 Jun 2023 Ana-Maria Cretu, Daniel Jones, Yves-Alexandre de Montjoye, Shruti Tople

Directly extending the shadow modelling technique from the black-box to the white-box setting has been shown, in general, not to perform better than black-box only attacks.

M$^2$M: A general method to perform various data analysis tasks from a differentially private sketch

no code implementations25 Nov 2022 Florimond Houssiau, Vincent Schellekens, Antoine Chatalic, Shreyas Kumar Annamraju, Yves-Alexandre de Montjoye

In this paper, we introduce the generic moment-to-moment (M$^2$M) method to perform a wide range of data exploration tasks from a single private sketch.

QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems

1 code implementation9 Nov 2022 Ana-Maria Cretu, Florimond Houssiau, Antoine Cully, Yves-Alexandre de Montjoye

We show the attacks found by QS to consistently equate or outperform, sometimes by a large margin, the best attacks from the literature.

Attribute

Correlation inference attacks against machine learning models

no code implementations16 Dec 2021 Ana-Maria Creţu, Florent Guépin, Yves-Alexandre de Montjoye

Second, we propose a model-based attack, showing how an attacker can exploit black-box access to the model to infer the correlations using shadow models trained on synthetic datasets.

Attribute BIG-bench Machine Learning +3

Modeling the Temporal Nature of Human Behavior for Demographics Prediction

1 code implementation20 Nov 2015 Bjarke Felbo, Pål Sundsøy, Alex 'Sandy' Pentland, Sune Lehmann, Yves-Alexandre de Montjoye

Mobile phone metadata is increasingly used for humanitarian purposes in developing countries as traditional data is scarce.

Gender Prediction Humanitarian

Cannot find the paper you are looking for? You can Submit a new open access paper.