Probing Language Models for Pre-training Data Detection
- URL: http://arxiv.org/abs/2406.01333v1
- Date: Mon, 3 Jun 2024 13:58:04 GMT
- Title: Probing Language Models for Pre-training Data Detection
- Authors: Zhenhua Liu, Tong Zhu, Chuanyuan Tan, Haonan Lu, Bing Liu, Wenliang Chen,
- Abstract summary: 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.
- Score: 11.37731401086372
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, 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. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy (Our code and dataset are available at https://github.com/zhliu0106/probing-lm-data).
Related papers
- Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification [34.37262622415682]
We propose a new adaptation framework called Data Adaptive Traceback.
Specifically, we utilize a zero-shot-based method to extract the most downstream task-related subset of the pre-training data.
We adopt a pseudo-label-based semi-supervised technique to reuse the pre-training images and a vision-language contrastive learning method to address the confirmation bias issue in semi-supervised learning.
arXiv Detail & Related papers (2024-07-11T18:01:58Z) - Extracting Training Data from Unconditional Diffusion Models [76.85077961718875]
diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI)
We aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization.
Based on the theoretical analysis, we propose a novel data extraction method called textbfSurrogate condItional Data Extraction (SIDE) that leverages a trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models.
arXiv Detail & Related papers (2024-06-18T16:20:12Z) - Learning with Noisy Foundation Models [95.50968225050012]
This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.
We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
arXiv Detail & Related papers (2024-03-11T16:22:41Z) - IT Intrusion Detection Using Statistical Learning and Testbed
Measurements [8.493936898320673]
We study automated intrusion detection in an IT infrastructure, specifically the problem of identifying the start of an attack.
We apply statistical learning methods, including Hidden Markov Model (HMM), Long Short-Term Memory (LSTM), and Random Forest (RFC)
We find that both HMM and LSTM can be effective in predicting attack start time, attack type, and attack actions.
arXiv Detail & Related papers (2024-02-20T15:25:56Z) - 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) - Machine Learning Based Missing Values Imputation in Categorical Datasets [2.5611256859404983]
This research looked into the use of machine learning algorithms to fill in the gaps in categorical datasets.
The emphasis was on ensemble models constructed using the Error Correction Output Codes framework.
Deep learning for missing data imputation has obstacles despite these encouraging results, including the requirement for large amounts of labeled data.
arXiv Detail & Related papers (2023-06-10T03:29:48Z) - Self-Supervised Learning for Data Scarcity in a Fatigue Damage
Prognostic Problem [0.0]
Self-Supervised Learning is a sub-category of unsupervised learning approaches.
This paper investigates whether pre-training DL models in a self-supervised way on unlabelled sensors data can be useful for Remaining Useful Life (RUL) estimation.
Results show that the self-supervised pre-trained models are able to significantly outperform the non-pre-trained models in downstream RUL prediction task.
arXiv Detail & Related papers (2023-01-20T06:45:32Z) - Temporal Output Discrepancy for Loss Estimation-based Active Learning [65.93767110342502]
We present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.
Our approach achieves superior performances than the state-of-the-art active learning methods on image classification and semantic segmentation tasks.
arXiv Detail & Related papers (2022-12-20T19:29:37Z) - Cluster-level pseudo-labelling for source-free cross-domain facial
expression recognition [94.56304526014875]
We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER)
Our method exploits self-supervised pretraining to learn good feature representations from the target data.
We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
arXiv Detail & Related papers (2022-10-11T08:24:50Z) - ALT-MAS: A Data-Efficient Framework for Active Testing of Machine
Learning Algorithms [58.684954492439424]
We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data.
The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
arXiv Detail & Related papers (2021-04-11T12:14:04Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
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.