A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish

• URL: http://arxiv.org/abs/2403.16139v1
• Date: Sun, 24 Mar 2024 13:21:58 GMT
• Title: A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish
• Authors: Masahiro Kaneko, Timothy Baldwin,
• Abstract summary: Large Language Models (LLMs) are trained on massive web-crawled corpora. LLMs produce leaked information in most cases despite less such data in their training set. Self-detection method showed superior performance compared to existing detection methods.
• Score: 47.3916421056009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to potential unauthorized generation of content or overestimation of performance. We establish the following three criteria concerning the leakage issues: (1) leakage rate: the proportion of leaked data in training data, (2) output rate: the ease of generating leaked data, and (3) detection rate: the detection performance of leaked versus non-leaked data. Despite the leakage rate being the origin of data leakage issues, it is not understood how it affects the output rate and detection rate. In this paper, we conduct an experimental survey to elucidate the relationship between the leakage rate and both the output rate and detection rate for personal information, copyrighted texts, and benchmark data. Additionally, we propose a self-detection approach that uses few-shot learning in which LLMs detect whether instances are present or absent in their training data, in contrast to previous methods that do not employ explicit learning. To explore the ease of generating leaked information, we create a dataset of prompts designed to elicit personal information, copyrighted text, and benchmarks from LLMs. Our experiments reveal that LLMs produce leaked information in most cases despite less such data in their training set. This indicates even small amounts of leaked data can greatly affect outputs. Our self-detection method showed superior performance compared to existing detection methods.

Related papers

• Improving Image Data Leakage Detection in Automotive Software [2.622385361961154]
  Data leakage is often overlooked during splitting data into train and test sets before training any ML/DL model. In this study, we conduct a computational experiment on the Cirrus dataset from our industrial partner Volvo Cars. We then evaluate the method on another public dataset, Kitti, which is a popular and widely accepted benchmark dataset in the automotive domain.
  arXiv  Detail & Related papers  (2024-10-29T13:37:45Z)
• 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)
• Entropy Law: The Story Behind Data Compression and LLM Performance [115.70395740286422]
  We find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.
  arXiv  Detail & Related papers  (2024-07-09T08:14:29Z)
• Probing Language Models for Pre-training Data Detection [11.37731401086372]
  We propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection.
  arXiv  Detail & Related papers  (2024-06-03T13:58:04Z)
• 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)
• Detecting Pretraining Data from Large Language Models [90.12037980837738]
  We study the pretraining data detection problem. Given a piece of text and black-box access to an LLM without knowing the pretraining data, can we determine if the model was trained on the provided text? We introduce a new detection method Min-K% Prob based on a simple hypothesis.
  arXiv  Detail & Related papers  (2023-10-25T17:21:23Z)
• From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying [10.919336198760808]
  We introduce a novel methodology to detect leaked data that are used to train classification models. textscLDSS involves injecting a small volume of synthetic data--characterized by local shifts in class distribution--into the owner's dataset. This enables the effective identification of models trained on leaked data through model querying alone.
  arXiv  Detail & Related papers  (2023-10-06T10:36:28Z)
• Black-box Dataset Ownership Verification via Backdoor Watermarking [67.69308278379957]
  We formulate the protection of released datasets as verifying whether they are adopted for training a (suspicious) third-party model. We propose to embed external patterns via backdoor watermarking for the ownership verification to protect them. Specifically, we exploit poison-only backdoor attacks ($e.g.$, BadNets) for dataset watermarking and design a hypothesis-test-guided method for dataset verification.
  arXiv  Detail & Related papers  (2022-08-04T05:32:20Z)

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.