The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text

• URL: http://arxiv.org/abs/2502.14921v1
• Date: Wed, 19 Feb 2025 15:30:30 GMT
• Title: The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
• Authors: Matthieu Meeus, Lukas Wutschitz, Santiago Zanella-Béguelin, Shruti Tople, Reza Shokri,
• Abstract summary: We design membership inference attacks (MIAs) that target data used to fine-tune pre-trained Large Language Models (LLMs)<n>We show that such data-based MIAs do significantly better than a random guess, meaning that synthetic data leaks information about the training data.<n>To tackle this problem, we leverage the mechanics of auto-regressive models to design canaries with an in-distribution prefix and a high-perplexity suffix.
• Score: 23.412546862849396
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: How much information about training samples can be gleaned from synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of privacy. In this paper, we design membership inference attacks (MIAs) that target data used to fine-tune pre-trained LLMs that are then used to synthesize data, particularly when the adversary does not have access to the fine-tuned model but only to the synthetic data. We show that such data-based MIAs do significantly better than a random guess, meaning that synthetic data leaks information about the training data. Further, we find that canaries crafted to maximize vulnerability to model-based MIAs are sub-optimal for privacy auditing when only synthetic data is released. Such out-of-distribution canaries have limited influence on the model's output when prompted to generate useful, in-distribution synthetic data, which drastically reduces their vulnerability. To tackle this problem, we leverage the mechanics of auto-regressive models to design canaries with an in-distribution prefix and a high-perplexity suffix that leave detectable traces in synthetic data. This enhances the power of data-based MIAs and provides a better assessment of the privacy risks of releasing synthetic data generated by LLMs.

Related papers

• Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection [1.03590082373586]
  Using synthetic data in membership evaluations may lead to false conclusions about model memorization and data leakage.<n>This issue could affect other evaluations using model signals such as loss where synthetic or machine-generated translated data substitutes for real-world samples.
  arXiv  Detail & Related papers  (2025-01-20T23:19:15Z)
• SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy [0.0]
  We investigate capability of Large Language Models (Ms) to generate synthetic datasets with Differential Privacy (DP) mechanisms.<n>Our approach incorporates DP-based noise injection methods, including Laplace and Gaussian distributions, into the data generation process.<n>We then evaluate the utility of these DP-enhanced synthetic datasets by comparing the performance of ML models trained on them against models trained on the original data.
  arXiv  Detail & Related papers  (2024-12-30T01:10:10Z)
• Little Giants: Synthesizing High-Quality Embedding Data at Scale [71.352883755806]
  We introduce SPEED, a framework that aligns open-source small models to efficiently generate large-scale embedding data. SPEED uses only less than 1/10 of the GPT API calls, outperforming the state-of-the-art embedding model E5_mistral when both are trained solely on their synthetic data.
  arXiv  Detail & Related papers  (2024-10-24T10:47:30Z)
• Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models [89.88010750772413]
  Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs) Our work delves into these specific flaws associated with question-answer (Q-A) pairs, a prevalent type of synthetic data, and presents a method based on unlearning techniques to mitigate these flaws. Our work has yielded key insights into the effective use of synthetic data, aiming to promote more robust and efficient LLM training.
  arXiv  Detail & Related papers  (2024-06-18T08:38:59Z)
• Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark [56.8042116967334]
  Synthetic data serves as an alternative in training machine learning models. ensuring that synthetic data mirrors the complex nuances of real-world data is a challenging task. This paper explores the potential of integrating data-centric AI techniques to guide the synthetic data generation process.
  arXiv  Detail & Related papers  (2023-10-25T20:32:02Z)
• Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data [9.061271587514215]
  We show how this assumption can be removed, allowing for MIAs to be performed using only the synthetic data. Our results show that MIAs are still successful, across two real-world datasets and two synthetic data generators.
  arXiv  Detail & Related papers  (2023-07-04T13:16:03Z)
• Synthetic data, real errors: how (not) to publish and use synthetic data [86.65594304109567]
  We show how the generative process affects the downstream ML task. We introduce Deep Generative Ensemble (DGE) to approximate the posterior distribution over the generative process model parameters.
  arXiv  Detail & Related papers  (2023-05-16T07:30:29Z)
• Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data [91.52783572568214]
  Synthetic data may become a dominant force in the machine learning world, promising a future where datasets can be tailored to individual needs. We discuss which fundamental challenges the community needs to overcome for wider relevance and application of synthetic data.
  arXiv  Detail & Related papers  (2023-04-07T16:38:40Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.