English
Related papers

Related papers: Single-Sample Black-Box Membership Inference Attac…

200 papers

Document Visual Question Answering (DocVQA) has introduced a new paradigm for end-to-end document understanding, and quickly became one of the standard benchmarks for multimodal LLMs. Automating document processing workflows, driven by…

Machine Learning · Computer Science 2025-02-07 Khanh Nguyen , Raouf Kerkouche , Mario Fritz , Dimosthenis Karatzas

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on…

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

Cryptography and Security · Computer Science 2025-12-09 Ruikai Zhou , Kang Yang , Xun Chen , Wendy Hui Wang , Guanhong Tao , Jun Xu

Determining which data samples were used to train a model, known as Membership Inference Attack (MIA), is a well-studied and important problem with implications on data privacy. SotA methods (which are black-box attacks) rely on training…

Machine Learning · Computer Science 2026-02-26 Yuval Golbari , Navve Wasserman , Gal Vardi , Michal Irani

Since machine learning model is often trained on a limited data set, the model is trained multiple times on the same data sample, which causes the model to memorize most of the training set data. Membership Inference Attacks (MIAs) exploit…

Machine Learning · Computer Science 2024-11-19 Depeng Chen , Xiao Liu , Jie Cui , Hong Zhong

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…

Cryptography and Security · Computer Science 2026-01-27 Mohammad Zare , Pirooz Shamsinejadbabaki

Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records belonging to the training dataset, several concerns remain…

Machine Learning · Computer Science 2026-01-23 Cristina Pêra , Tânia Carvalho , Maxime Cordy , Luís Antunes

In this paper we develop state-of-the-art privacy attacks against Large Language Models (LLMs), where an adversary with some access to the model tries to learn something about the underlying training data. Our headline results are new…

Cryptography and Security · Computer Science 2024-07-16 Jeffrey G. Wang , Jason Wang , Marvin Li , Seth Neel

Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data…

Cryptography and Security · Computer Science 2022-10-31 Mauro Conti , Jiaxin Li , Stjepan Picek

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-tuning a Latent…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Lauritz Christian Holme , Anton Mosquera Storgaard , Siavash Arjomand Bigdeli

Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, existing methods often misinfer non-members as members, leading…

Machine Learning · Computer Science 2025-05-07 Saleh Zare Zade , Yao Qiang , Xiangyu Zhou , Hui Zhu , Mohammad Amin Roshani , Prashant Khanduri , Dongxiao Zhu

Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and other sophisticated threats. Many practical black-box MIAs…

Machine Learning · Computer Science 2023-10-13 Jihye Choi , Shruti Tople , Varun Chandrasekaran , Somesh Jha

Model inversion attacks (MIAs) seek to infer the private training data of a target classifier by generating synthetic images that reflect the characteristics of the target class through querying the model. However, prior studies have relied…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Xinhao Liu , Yingzhao Jiang , Zetao Lin

Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and…

Machine Learning · Computer Science 2026-01-27 Pedram Zaree , Md Abdullah Al Mamun , Yue Dong , Ihsen Alouani , Nael Abu-Ghazaleh

Membership inference attacks (MIA) aim to infer whether a particular data point is part of the training dataset of a model. In this paper, we propose a new task in the context of LLM privacy: entity-level discovery of membership risk…

Machine Learning · Computer Science 2025-11-04 Ali Satvaty , Suzan Verberne , Fatih Turkmen

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Machine Learning · Computer Science 2025-06-03 Toan Tran , Ruixuan Liu , Li Xiong

The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if…

Machine Learning · Computer Science 2024-06-11 Pratyush Maini , Hengrui Jia , Nicolas Papernot , Adam Dziedzic

Whether LLMs memorize their training data and what this means, from measuring privacy leakage to detecting copyright violations, has become a rapidly growing area of research. In the last few months, more than 10 new methods have been…

Computation and Language · Computer Science 2025-03-10 Matthieu Meeus , Igor Shilov , Shubham Jain , Manuel Faysse , Marek Rei , Yves-Alexandre de Montjoye

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…

Cryptography and Security · Computer Science 2025-03-13 Daniel Jiménez-López , Nuria Rodríguez-Barroso , M. Victoria Luzón , Francisco Herrera

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Machine Learning · Computer Science 2026-05-25 Anthony Hughes , Alexander Goldberg , Prince Jha , Adam Perer , Nikolaos Aletras , Niloofar Mireshghallah