mlsanityData to 7 Oct 2026

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

arXiv 2505.03490 ↗First posted 6 May 2025cs.LG cs.AIcited by 0

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 14 of its 20 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

14 of 20 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration10 Nov
  2. 2023Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models30 Oct
  3. 2022Membership Inference Attacks by Exploiting Loss Trajectory31 Aug
  4. 2021Membership Inference Attacks From First Principles7 Dec
  5. 2021EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning25 Aug

Other references · 9

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2020Extracting Training Data from Large Language Modelscited by 2,144
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 167
  5. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  6. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  7. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  8. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  9. 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 50

Built on by

Not cited yet.