English
Related papers

Related papers: Training Data Extraction From Pre-trained Language…

200 papers

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Computation and Language · Computer Science 2024-09-04 Myung Gyo Oh , Hong Eun Ahn , Leo Hyun Park , Taekyoung Kwon

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover…

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Daphne Ippolito , Matthew Jagielski , Katherine Lee , Florian Tramer , Chiyuan Zhang

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the…

Cryptography and Security · Computer Science 2024-03-26 Arijit Ghosh Chowdhury , Md Mofijul Islam , Vaibhav Kumar , Faysal Hossain Shezan , Vaibhav Kumar , Vinija Jain , Aman Chadha

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…

Machine Learning · Computer Science 2025-02-25 Mansi Gupta , Nikhar Waghela , Sarthak Gupta , Shourya Goel , Sanjif Shanmugavelu

This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this…

Cryptography and Security · Computer Science 2026-04-16 Rafiqul Rabin , Sean McGregor , Nick Judd

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

Cryptography and Security · Computer Science 2021-02-24 Huseyin A. Inan , Osman Ramadan , Lukas Wutschitz , Daniel Jones , Victor Rühle , James Withers , Robert Sim

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…

This work quantifies the risk of training data leakage from LLMs (Large Language Models) using sequence-level probabilities. Computing extraction probabilities for individual sequences provides finer-grained information than has been…

Computation and Language · Computer Science 2025-04-17 Trishita Tiwari , G. Edward Suh

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…

Machine Learning · Computer Science 2024-05-07 George-Octavian Barbulescu , Peter Triantafillou

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

Cryptography and Security · Computer Science 2022-12-21 Nikhil Kandpal , Eric Wallace , Colin Raffel

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Neural models that do not rely on pre-training have excelled in the keyphrase generation task with large annotated datasets. Meanwhile, new approaches have incorporated pre-trained language models (PLMs) for their data efficiency. However,…

Computation and Language · Computer Science 2024-02-26 Di Wu , Wasi Uddin Ahmad , Kai-Wei Chang

When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new practical data extraction attack that we call "neural…

Cryptography and Security · Computer Science 2024-03-05 Ashwinee Panda , Christopher A. Choquette-Choo , Zhengming Zhang , Yaoqing Yang , Prateek Mittal

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer…

Artificial Intelligence · Computer Science 2024-11-13 Meng Yang , Tianqing Zhu , Chi Liu , WanLei Zhou , Shui Yu , Philip S. Yu

Large Language Models (LLMs) have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack…

Cryptography and Security · Computer Science 2025-05-05 Zhiyu Liao , Kang Chen , Yuanguo Lin , Kangkang Li , Yunxuan Liu , Hefeng Chen , Xingwang Huang , Yuanhui Yu

Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…

Machine Learning · Computer Science 2024-04-08 Jie Xu , Zihan Wu , Cong Wang , Xiaohua Jia

Does GPT know you? The answer depends on your level of public recognition; however, if your information was available on a website, the answer could be yes. Most Large Language Models (LLMs) memorize training data to some extent. Thus, even…

Machine Learning · Computer Science 2025-06-19 Henrik Nolte , Michèle Finck , Kristof Meding

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

Computation and Language · Computer Science 2026-03-04 Xiaoyu Luo , Wenrui Yu , Qiongxiu Li , Johannes Bjerva

Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…

Cryptography and Security · Computer Science 2025-08-22 Elena Sofia Ruzzetti , Giancarlo A. Xompero , Davide Venditti , Fabio Massimo Zanzotto