English
Related papers

Related papers: Provably Confidential Language Modelling

200 papers

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for…

Cryptography and Security · Computer Science 2025-06-03 Arun Ganesh , Brendan McMahan , Milad Nasr , Thomas Steinke , Abhradeep Thakurta

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…

Machine Learning · Computer Science 2024-05-06 Fan Wu , Huseyin A. Inan , Arturs Backurs , Varun Chandrasekaran , Janardhan Kulkarni , Robert Sim

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

Computation and Language · Computer Science 2024-05-24 Aldo Gael Carranza , Rezsa Farahani , Natalia Ponomareva , Alex Kurakin , Matthew Jagielski , Milad Nasr

Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are crucial to meet memory and inference time requirements, as…

Machine Learning · Computer Science 2024-07-03 Da Yu , Sivakanth Gopi , Janardhan Kulkarni , Zinan Lin , Saurabh Naik , Tomasz Lukasz Religa , Jian Yin , Huishuai Zhang

Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information (PII), which could be exposed to third parties hosting these…

Cryptography and Security · Computer Science 2026-03-30 Shashie Dilhara Batan Arachchige , Hassan Jameel Asghar , Benjamin Zi Hao Zhao , Dinusha Vatsalan , Dali Kaafar

This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models---a common type of machine-learning model. Because such…

Machine Learning · Computer Science 2019-07-17 Nicholas Carlini , Chang Liu , Úlfar Erlingsson , Jernej Kos , Dawn Song

Privacy preservation remains a key challenge in data mining and Natural Language Understanding (NLU). Previous research shows that the input text or even text embeddings can leak private information. This concern motivates our research on…

Computation and Language · Computer Science 2021-08-23 Chen Qu , Weize Kong , Liu Yang , Mingyang Zhang , Michael Bendersky , Marc Najork

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Cryptography and Security · Computer Science 2025-08-28 Zhan Shi , Yefeng Yuan , Yuhong Liu , Liang Cheng , Yi Fang

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

We propose CHRT (Control Hidden Representation Transformation) - a controlled language generation framework that steers large language models to generate text pertaining to certain attributes (such as toxicity). CHRT gains attribute control…

Computation and Language · Computer Science 2023-06-01 Vaibhav Kumar , Hana Koorehdavoudi , Masud Moshtaghi , Amita Misra , Ankit Chadha , Emilio Ferrara

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident…

Computer Vision and Pattern Recognition · Computer Science 2020-07-16 Yang Zou , Zhiding Yu , Xiaofeng Liu , B. V. K. Vijaya Kumar , Jinsong Wang

Large language models specialized for code (CodeLLMs) have demonstrated remarkable capabilities in generating code snippets, documentation, and test cases. However, despite their promising capabilities, CodeLLMs can inadvertently memorize…

Software Engineering · Computer Science 2025-12-15 Melih Catal , Pooja Rani , Harald C. Gall

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

Software Engineering · Computer Science 2025-09-18 Zhaoyang Chu , Yao Wan , Zhikun Zhang , Di Wang , Zhou Yang , Hongyu Zhang , Pan Zhou , Xuanhua Shi , Hai Jin , David Lo

Large language models (LLMs), especially those based on the Transformer architecture, have had a profound impact on various aspects of daily life, such as natural language processing, content generation, research methodologies, and more.…

Machine Learning · Computer Science 2024-10-15 Yeqi Gao , Zhao Song , Xin Yang , Yufa Zhou

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and…

High-quality training data has proven crucial for developing performant large language models (LLMs). However, commercial LLM providers disclose few, if any, details about the data used for training. This lack of transparency creates…

With the advance of language models, privacy protection is receiving more attention. Training data extraction is therefore of great importance, as it can serve as a potential tool to assess privacy leakage. However, due to the difficulty of…

Computation and Language · Computer Science 2023-06-02 Weichen Yu , Tianyu Pang , Qian Liu , Chao Du , Bingyi Kang , Yan Huang , Min Lin , Shuicheng Yan

While recent research increasingly showcases the remarkable capabilities of Large Language Models (LLMs), it is equally crucial to examine their associated risks. Among these, privacy and security vulnerabilities are particularly…

Computation and Language · Computer Science 2026-01-21 Ali Satvaty , Suzan Verberne , Fatih Turkmen

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…

Computation and Language · Computer Science 2023-05-08 Davut Emre Tasar , Ceren Ocal Tasar

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