# Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage

arXiv: https://arxiv.org/abs/2603.24213 · HTML: https://mlsanity.com/paper/2603.24213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [SAITS: Self-Attention-based Imputation for Time Series](https://mlsanity.com/paper/2202.08516/) (2022)
- [Reconstruction and Membership Inference Attacks against Generative Models](https://mlsanity.com/paper/1906.03006/) (2019)
- [Membership Inference Attacks by Exploiting Loss Trajectory](https://mlsanity.com/paper/2208.14933/) (2022)
- [Node-Level Membership Inference Attacks Against Graph Neural Networks](https://mlsanity.com/paper/2102.05429/) (2021)
- [EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning](https://mlsanity.com/paper/2108.11023/) (2021)
- [AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning](https://mlsanity.com/paper/1805.04810/) (2018)
- [Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications](https://mlsanity.com/paper/2110.08760/) (2021)
- [Are Attribute Inference Attacks Just Imputation?](https://mlsanity.com/paper/2209.01292/) (2022)
- [The ASHRAE Great Energy Predictor III competition: Overview and results](https://mlsanity.com/paper/2007.06933/) (2020)
- [Disparate Privacy Vulnerability: Targeted Attribute Inference Attacks and Defenses](https://mlsanity.com/paper/2504.04033/) (2025)

## Abstract (arXiv)

Deep learning models for time series imputation are now essential in fields such as healthcare, the Internet of Things (IoT), and finance. However, their deployment raises critical privacy concerns. Beyond the well-known issue of unintended memorization, which has been extensively studied in generative models, we demonstrate that time series models are vulnerable to inference attacks in a black-box setting. In this work, we introduce a two-stage attack framework comprising: (1) a novel membership inference attack based on a reference model that improves detection accuracy, even for models robust to overfitting-based attacks, and (2) the first attribute inference attack that predicts sensitive characteristics of the training data for timeseries imputation model. We evaluate these attacks on attention-based and autoencoder architectures in two scenarios: models that are trained from scratch, and fine-tuned models where the adversary has access to the initial weights. Our experimental results demonstrate that the proposed membership attack retrieves a significant portion of the training data with a tpr@top25% score significantly higher than a naive attack baseline. We show that our membership attack also provides a good insight of whether attribute inference will work (with a precision of 90% instead of 78% in the genral case).