English
Related papers

Related papers: Provably Confidential Language Modelling

200 papers

Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private information from these datasets. Differentially private SGD [DP-SGD]…

Machine Learning · Computer Science 2024-09-26 Francisco Aguilera-Martínez , Fernando Berzal

Large language models (LLMs) are complex artificial intelligence systems capable of understanding, generating and translating human language. They learn language patterns by analyzing large amounts of text data, allowing them to perform…

Cryptography and Security · Computer Science 2024-03-15 Biwei Yan , Kun Li , Minghui Xu , Yueyan Dong , Yue Zhang , Zhaochun Ren , Xiuzhen Cheng

Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text.…

Computation and Language · Computer Science 2023-10-18 Stefan Arnold , Nils Kemmerzell , Annika Schreiner

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…

Computation and Language · Computer Science 2022-07-19 Weiyan Shi , Aiqi Cui , Evan Li , Ruoxi Jia , Zhou Yu

Recent research shows that large language models are susceptible to privacy attacks that infer aspects of the training data. However, it is unclear if simpler generative models, like topic models, share similar vulnerabilities. In this…

Cryptography and Security · Computer Science 2024-09-24 Nico Manzonelli , Wanrong Zhang , Salil Vadhan

In this paper we propose the federated learning algorithm Fed-PLT to overcome the challenges of (i) expensive communications and (ii) privacy preservation. We address (i) by allowing for both partial participation and local training, which…

Machine Learning · Computer Science 2024-12-02 Nicola Bastianello , Changxin Liu , Karl H. Johansson

The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks. While CLIP has revolutionized multimodal learning through joint training on images and text, its potential to unintentionally disclose…

Machine Learning · Computer Science 2024-03-04 Alyssa Huang , Peihan Liu , Ryumei Nakada , Linjun Zhang , Wanrong Zhang

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for discovery of hidden semantic architecture of text datasets, and plays a fundamental role in many machine learning applications. However, like many other machine…

Machine Learning · Computer Science 2019-07-02 Fangyuan Zhao , Xuebin Ren , Shusen Yang , Xinyu Yang

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Artificial Intelligence · Computer Science 2025-02-04 Hao Li , Di Huang , Ziyu Wang , Amir M. Rahmani

Large Language Models (LLMs) have demonstrated significant improvements in reasoning capabilities through supervised fine-tuning and reinforcement learning. However, when training reasoning models, these approaches are primarily applicable…

Computation and Language · Computer Science 2025-05-16 Yoichi Ishibashi , Taro Yano , Masafumi Oyamada

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

Cryptography and Security · Computer Science 2025-03-12 Haodi Wang , Tangyu Jiang , Yu Guo , Chengjun Cai , Cong Wang , Xiaohua Jia

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

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Cryptography and Security · Computer Science 2025-11-18 Hasini Jayathilaka

Large language models (LLMs), like ChatGPT, have greatly simplified text generation tasks. However, they have also raised concerns about privacy risks such as data leakage and unauthorized data collection. Existing solutions for…

Cryptography and Security · Computer Science 2026-03-19 Meng Tong , Kejiang Chen , Jie Zhang , Yuang Qi , Weiming Zhang , Nenghai Yu , Tianwei Zhang , Zhikun Zhang

Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and…

Computation and Language · Computer Science 2022-11-16 David Ifeoluwa Adelani , Ali Davody , Thomas Kleinbauer , Dietrich Klakow

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

Computation and Language · Computer Science 2024-04-12 Kennedy Edemacu , Xintao Wu

Social chatbots, also known as chit-chat chatbots, evolve rapidly with large pretrained language models. Despite the huge progress, privacy concerns have arisen recently: training data of large language models can be extracted via model…

Computation and Language · Computer Science 2022-05-23 Haoran Li , Yangqiu Song , Lixin Fan

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…

Computation and Language · Computer Science 2023-10-04 Yang Chen , Ethan Mendes , Sauvik Das , Wei Xu , Alan Ritter

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…

Computation and Language · Computer Science 2024-06-19 Victoria Smith , Ali Shahin Shamsabadi , Carolyn Ashurst , Adrian Weller

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training…

Machine Learning · Computer Science 2021-10-06 Hossein Esfandiari , Vahab Mirrokni , Umar Syed , Sergei Vassilvitskii