Search Results for author:
Found 10 papers, 3 papers with code
Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks
We evaluate six neural networks architectures as the embedding model.
Copyright Traps for Large Language Models
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.
Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models
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.
Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data
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
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.
Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
We here present the first systematic analysis of the causes of misalignment in shadow models and show the use of a different weight initialisation to be the main cause.
M$^2$M: A general method to perform various data analysis tasks from a differentially private sketch
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
We show the attacks found by QS to consistently equate or outperform, sometimes by a large margin, the best attacks from the literature.
Correlation inference attacks against machine learning models
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.
Modeling the Temporal Nature of Human Behavior for Demographics Prediction
Mobile phone metadata is increasingly used for humanitarian purposes in developing countries as traditional data is scarce.
