MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs

• URL: http://arxiv.org/abs/2412.07261v2
• Date: Sun, 16 Feb 2025 06:20:55 GMT
• Title: MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs
• Authors: Zhenpeng Wu, Jian Lou, Zibin Zheng, Chuan Chen,
• Abstract summary: We introduce MemHunter, which trains a memory-inducing LLM and employs hypothesis testing to efficiently detect memorization at the dataset level. MemHunter is the first method capable of dataset-level memorization detection, providing a critical tool for assessing privacy risks in large-scale datasets.
• Score: 28.593941036010417
• License:
• Abstract: Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily sample-specific, relying on manually crafted or discretely optimized memory-inducing prompts generated on a per-sample basis, which become impractical for dataset-level detection due to the prohibitive computational cost of iterating through all samples. In real-world scenarios, data owners may need to verify whether a susceptible LLM has memorized their dataset, particularly if the LLM may have collected the data from the web without authorization. To address this, we introduce MemHunter, which trains a memory-inducing LLM and employs hypothesis testing to efficiently detect memorization at the dataset level, without requiring sample-specific memory inducing. Experiments on models like Pythia and Llama demonstrate that MemHunter can extract up to 40% more training data than existing methods under constrained time resources and reduce search time by up to 80% when integrated as a plug-in. Crucially, MemHunter is the first method capable of dataset-level memorization detection, providing a critical tool for assessing privacy risks in LLMs powered by large-scale datasets.

Related papers

• Training on the Benchmark Is Not All You Need [52.01920740114261]
  We propose a simple and effective data leakage detection method based on the contents of multiple-choice options. Our method is able to work under black-box conditions without access to model training data or weights. We evaluate the degree of data leakage of 31 mainstream open-source LLMs on four benchmark datasets.
  arXiv  Detail & Related papers  (2024-09-03T11:09:44Z)
• Evaluating LLM-based Personal Information Extraction and Countermeasures [63.91918057570824]
  Large language model (LLM) based personal information extraction can be benchmarked. LLM can be misused by attackers to accurately extract various personal information from personal profiles. prompt injection can defend against strong LLM-based attacks, reducing the attack to less effective traditional ones.
  arXiv  Detail & Related papers  (2024-08-14T04:49:30Z)
• Anomaly Detection of Tabular Data Using LLMs [54.470648484612866]
  We show that pre-trained large language models (LLMs) are zero-shot batch-level anomaly detectors. We propose an end-to-end fine-tuning strategy to bring out the potential of LLMs in detecting real anomalies.
  arXiv  Detail & Related papers  (2024-06-24T04:17:03Z)
• Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research [0.23982628363233693]
  We investigate whether Large Language Models (LLMs) have had access to standard Human Activity Recognition (HAR) datasets during training. Most contemporary LLMs are trained on virtually the entire (accessible) internet -- potentially including standard HAR datasets. For the Daphnet dataset in particular, GPT-4 is able to reproduce blocks of sensor readings.
  arXiv  Detail & Related papers  (2024-06-09T19:38:27Z)
• Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models [21.10890310571397]
  Large Language Models (LLMs) can be applied to a diverse set of tasks, but the critical issues of data contamination and memorization are often glossed over. This work introduces a variety of different techniques to assess whether a language model has seen a dataset during training. We then compare the few-shot learning performance of LLMs on datasets that were seen during training to the performance on datasets released after training.
  arXiv  Detail & Related papers  (2024-04-09T10:58:21Z)
• LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement [79.31084387589968]
  Pretrained large language models (LLMs) are currently state-of-the-art for solving the vast majority of natural language processing tasks. We propose LLM2LLM, a data augmentation strategy that uses a teacher LLM to enhance a small seed dataset. We achieve improvements up to 24.2% on the GSM8K dataset, 32.6% on CaseHOLD, 32.0% on SNIPS, 52.6% on TREC and 39.8% on SST-2 over regular fine-tuning in the low-data regime.
  arXiv  Detail & Related papers  (2024-03-22T08:57:07Z)
• Elephants Never Forget: Testing Language Models for Memorization of Tabular Data [21.912611415307644]
  Large Language Models (LLMs) can be applied to a diverse set of tasks, but the critical issues of data contamination and memorization are often glossed over. We introduce a variety of different techniques to assess the degrees of contamination, including statistical tests for conditional distribution modeling and four tests that identify memorization.
  arXiv  Detail & Related papers  (2024-03-11T12:07:13Z)
• Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs [61.04246774006429]
  We introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent. We observe that our instruction-based prompts generate outputs with 23.7% higher overlap with training data compared to the baseline prefix-suffix measurements. Our findings show that instruction-tuned models can expose pre-training data as much as their base-models, if not more so, and using instructions proposed by other LLMs can open a new avenue of automated attacks.
  arXiv  Detail & Related papers  (2024-03-05T19:32:01Z)
• How to Train Data-Efficient LLMs [56.41105687693619]
  We study data-efficient approaches for pre-training language models (LLMs) We find that Ask-LLM and Density sampling are the best methods in their respective categories. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories.
  arXiv  Detail & Related papers  (2024-02-15T02:27:57Z)

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.