A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)

Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM) algorithm. The LBRM method leverages a reference model to enhance the accuracy of membership inference attacks, distinguishing between training and test data. Our contributions are twofold: first, we propose an innovative method to effectively extract and identify memorized training data, significantly improving detection accuracy. On average, without fine-tuning, the AUROC improved by approximately 40\%. With fine-tuning, the AUROC increased by approximately 60\%. Second, we validate our approach through membership inference attacks on two types of architectures designed for time series imputation, demonstrating the robustness and versatility of the LBRM approach in different contexts. These results highlight the significant enhancement in detection accuracy provided by the LBRM approach, addressing privacy risks in time series imputation models.

Practical and Ready-to-Use Methodology to Assess the re-identification Risk in Anonymized Datasets

To prove that a dataset is sufficiently anonymized, many privacy policies suggest that a re-identification risk assessment be performed, but do not provide a precise methodology for doing so, leaving the industry alone with the problem. This paper proposes a practical and ready-to-use methodology for re-identification risk assessment, the originality of which is manifold: (1) it is the first to follow well-known risk analysis methods (e.g. EBIOS) that have been used in the cybersecurity field for years, which consider not only the ability to perform an attack, but also the impact such an attack can have on an individual; (2) it is the first to qualify attributes and values of attributes with e.g. degree of exposure, as known real-world attacks mainly target certain types of attributes and not others.