English
Related papers

Related papers: Tab-MIA: A Benchmark Dataset for Membership Infere…

200 papers

Retrieval Augmented Generation (RAG) systems have shown great promise in natural language processing. However, their reliance on data stored in a retrieval database, which may contain proprietary or sensitive information, introduces new…

Cryptography and Security · Computer Science 2025-03-10 Maya Anderson , Guy Amit , Abigail Goldsteen

Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs, which embed the ability to use tools or APIs directly into the parametric knowledge of LLMs. Tool-augmented LLMs need the ability to forget…

Machine Learning · Computer Science 2025-08-07 Jiali Cheng , Hadi Amiri

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by conditioning on demonstrations of question-answer pairs and it has been shown to have comparable performance to costly model retraining and fine-tuning.…

Cryptography and Security · Computer Science 2024-03-12 Alycia N. Carey , Karuna Bhaila , Kennedy Edemacu , Xintao Wu

Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership Inference Attacks (MIAs), which aim to determine whether a…

Machine Learning · Computer Science 2025-03-28 Gongxi Zhu , Donghao Li , Hanlin Gu , Yuan Yao , Lixin Fan , Yuxing Han

Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have increased drastically. This raises the key question of…

Artificial Intelligence · Computer Science 2024-05-07 Robin Staab , Mark Vero , Mislav Balunović , Martin Vechev

Large Language Models (LLMs) are increasingly used in a variety of applications, but concerns around membership inference have grown in parallel. Previous efforts focus on black-to-grey-box models, thus neglecting the potential benefit from…

Cryptography and Security · Computer Science 2025-01-13 Luis Ibanez-Lissen , Lorena Gonzalez-Manzano , Jose Maria de Fuentes , Nicolas Anciaux , Joaquin Garcia-Alfaro

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

A membership inference attack (MIA) poses privacy risks for the training data of a machine learning model. With an MIA, an attacker guesses if the target data are a member of the training dataset. The state-of-the-art defense against MIAs,…

Cryptography and Security · Computer Science 2022-11-16 Rishav Chourasia , Batnyam Enkhtaivan , Kunihiro Ito , Junki Mori , Isamu Teranishi , Hikaru Tsuchida

This paper extends the Classification Error Gauge (x-CEG) framework, originally developed for measuring the privacy-utility trade-off in tabular datasets, to privacy auditing of Large Language Models (LLMs). We propose LLM-CEG, a systematic…

Cryptography and Security · Computer Science 2026-04-28 Kato Mivule

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment…

Cryptography and Security · Computer Science 2025-05-19 Yidan Wang , Yanan Cao , Yubing Ren , Fang Fang , Zheng Lin , Binxing Fang

This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract…

Computer Vision and Pattern Recognition · Computer Science 2023-11-17 Thomas Cilloni , Charles Fleming , Charles Walter

Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorization. We propose a principled revision of memorization…

Computation and Language · Computer Science 2026-01-08 Xiaoyu Luo , Yiyi Chen , Qiongxiu Li , Johannes Bjerva

Large language models (LLMs) have demonstrated significant success in various domain-specific tasks, with their performance often improving substantially after fine-tuning. However, fine-tuning with real-world data introduces privacy risks.…

Cryptography and Security · Computer Science 2025-01-30 Atilla Akkus , Masoud Poorghaffar Aghdam , Mingjie Li , Junjie Chu , Michael Backes , Yang Zhang , Sinem Sav

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…

Cryptography and Security · Computer Science 2024-05-09 Chunyan Zheng , Keke Sun , Wenhao Zhao , Haibo Zhou , Lixin Jiang , Shaoyang Song , Chunlai Zhou

How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of…

Computation and Language · Computer Science 2026-02-13 Matthieu Meeus , Lukas Wutschitz , Santiago Zanella-Béguelin , Shruti Tople , Reza Shokri

Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is…

Data used to train machine learning (ML) models can be sensitive. Membership inference attacks (MIAs), attempting to determine whether a particular data record was used to train an ML model, risk violating membership privacy. ML model…

Cryptography and Security · Computer Science 2022-09-07 Vasisht Duddu , Sebastian Szyller , N. Asokan

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

The widespread collection and sharing of location data, even in aggregated form, raises major privacy concerns. Previous studies used meta-classifier-based membership inference attacks~(MIAs) with multi-layer perceptrons~(MLPs) to estimate…

Cryptography and Security · Computer Science 2024-12-31 Yuhan Liu , Florent Guepin , Igor Shilov , Yves-Alexandre De Montjoye

Recent work in the privacy literature shows that sample-targeted membership inference attacks (MIAs) significantly outperform untargeted approaches by a wide margin. Motivated by this observation, we address the following question: can the…

Machine Learning · Statistics 2026-05-27 Valentin Dorseuil , Jamal Atif , Olivier Cappé