English
Related papers

Related papers: Do Membership Inference Attacks Work on Large Lang…

200 papers

Membership Inference Attacks (MIAs) determine whether a specific data point was included in the training set of a target model. In this paper, we introduce the Semantic Membership Inference Attack (SMIA), a novel approach that enhances MIA…

Machine Learning · Computer Science 2024-06-17 Hamid Mozaffari , Virendra J. Marathe

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or…

Cryptography and Security · Computer Science 2018-02-15 Yunhui Long , Vincent Bindschaedler , Lei Wang , Diyue Bu , Xiaofeng Wang , Haixu Tang , Carl A. Gunter , Kai Chen

Determining whether a dataset was part of a machine learning model's training data pool can reveal privacy vulnerabilities, a challenge often addressed through membership inference attacks (MIAs). Traditional MIAs typically require access…

Machine Learning · Computer Science 2025-06-03 Yongchao Huang

Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…

Cryptography and Security · Computer Science 2023-06-16 Thomas Humphries , Simon Oya , Lindsey Tulloch , Matthew Rafuse , Ian Goldberg , Urs Hengartner , Florian Kerschbaum

Large language models (LLMs) have demonstrated great performance across various benchmarks, showing potential as general-purpose task solvers. However, as LLMs are typically trained on vast amounts of data, a significant concern in their…

Computation and Language · Computer Science 2025-05-13 Yujuan Fu , Ozlem Uzuner , Meliha Yetisgen , Fei Xia

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

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…

Cryptography and Security · Computer Science 2025-02-10 Yuke Hu , Zheng Li , Zhihao Liu , Yang Zhang , Zhan Qin , Kui Ren , Chun Chen

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this…

Machine Learning · Computer Science 2026-02-13 Nicolas Johansson , Tobias Olsson , Daniel Nilsson , Johan Östman , Fazeleh Hoseini

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

A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of…

Machine Learning · Computer Science 2021-09-20 Bogdan Kulynych , Mohammad Yaghini , Giovanni Cherubin , Michael Veale , Carmela Troncoso

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

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

Membership Inference Attacks (MIAs) are widely used to quantify training data memorization and assess privacy risks. Standard evaluation requires repeated retraining, which is computationally costly for large models. One-run methods (single…

Machine Learning · Computer Science 2026-02-06 Mathieu Even , Clément Berenfeld , Linus Bleistein , Tudor Cebere , Julie Josse , Aurélien Bellet

Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks (MIAs) are designed to ascertain whether specific data was…

Cryptography and Security · Computer Science 2026-05-29 Puwei Lian , Yujun Cai , Songze Li , Bingkun Bao

With the widespread application of large language models (LLM), concerns about the privacy leakage of model training data have increasingly become a focus. Membership Inference Attacks (MIAs) have emerged as a critical tool for evaluating…

Robotics · Computer Science 2024-12-24 Zichen Song , Sitan Huang , Zhongfeng Kang

Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of-the-art attacks typically rely on training multiple reference models to approximate the…

Machine Learning · Computer Science 2026-05-26 Zhenlong Liu , Wenyu Jiang , Feng Zhou , Hongxin Wei

Membership inference attacks (MIAs) pose a critical privacy threat to fine-tuned large language models (LLMs), especially when models are adapted to domain-specific tasks using sensitive data. While prior black-box MIA techniques rely on…

Cryptography and Security · Computer Science 2025-12-23 Zhexi Lu , Hongliang Chi , Nathalie Baracaldo , Swanand Ravindra Kadhe , Yuseok Jeon , Lei Yu

Membership inference attacks (MIAs) are used to test practical privacy of machine learning models. MIAs complement formal guarantees from differential privacy (DP) under a more realistic adversary model. We analyse MIA vulnerability of…

Cryptography and Security · Computer Science 2026-02-03 Marlon Tobaben , Hibiki Ito , Joonas Jälkö , Yuan He , Antti Honkela

A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models. Further, the work of \cite{somesh-overfit} shows that such membership inference…

Cryptography and Security · Computer Science 2019-10-15 Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Raghav Bhaskar , Mohamed Ali Kaafar

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