English
Related papers

Related papers: AttenMIA: LLM Membership Inference Attack through …

200 papers

Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likelihoods or text generations. In this work, we introduce…

Machine Learning · Computer Science 2026-02-24 Junjie Oscar Yin , John X. Morris , Vitaly Shmatikov , Sewon Min , Hannaneh Hajishirzi

Cognitive diagnosis models (CDMs) are pivotal for creating fine-grained learner profiles in modern intelligent education platforms. However, these models are trained on sensitive student data, raising significant privacy concerns. While…

Cryptography and Security · Computer Science 2025-11-10 Mingliang Hou , Yinuo Wang , Teng Guo , Zitao Liu , Wenzhou Dou , Jiaqi Zheng , Renqiang Luo , Mi Tian , Weiqi Luo

The data used to train deep neural network (DNN) models in applications such as healthcare and finance typically contain sensitive information. A DNN model may suffer from overfitting. Overfitted models have been shown to be susceptible to…

Machine Learning · Computer Science 2022-12-19 Arezoo Rajabi , Dinuka Sahabandu , Luyao Niu , Bhaskar Ramasubramanian , Radha Poovendran

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

Cryptography and Security · Computer Science 2018-12-18 Ahmed Salem , Yang Zhang , Mathias Humbert , Pascal Berrang , Mario Fritz , Michael Backes

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

Membership inference attacks (MIAs) are widely used to empirically assess privacy risks in machine learning models, both providing model-level vulnerability metrics and identifying the most vulnerable training samples. State-of-the-art…

Machine Learning · Computer Science 2025-06-13 Joseph Pollock , Igor Shilov , Euodia Dodd , Yves-Alexandre de Montjoye

Membership inference attacks (MIAs) aim to determine whether a sample was part of a model's training set, posing serious privacy risks for modern machine-learning systems. Existing MIAs primarily rely on static indicators, such as loss or…

Artificial Intelligence · Computer Science 2026-02-06 Amit Kravchik Taub , Fred M. Grabovski , Guy Amit , Yisroel Mirsky

Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches…

Machine Learning · Computer Science 2024-05-30 Xingli Fang , Jung-Eun Kim

Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known…

Cryptography and Security · Computer Science 2023-10-03 Hongsheng Hu , Xuyun Zhang , Zoran Salcic , Lichao Sun , Kim-Kwang Raymond Choo , Gillian Dobbie

Vision-Language Models (VLMs) have achieved remarkable success, yet their reliance on massive datasets and unintended memorization of training data raise significant data security risk. Membership Inference Attacks (MIAs) aim to assess…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jiaqing Li , Yajuan Lu , Xiaochuan Shi , Gang Wu , ZhongYuan Wang , Chao Liang

This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate Gradient (GCG) strategy. We first observe a positive…

Computation and Language · Computer Science 2024-10-14 Zijun Wang , Haoqin Tu , Jieru Mei , Bingchen Zhao , Yisen Wang , Cihang Xie

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

Machine Learning · Computer Science 2025-06-03 Rongzhe Wei , Mufei Li , Mohsen Ghassemi , Eleonora Kreačić , Yifan Li , Xiang Yue , Bo Li , Vamsi K. Potluru , Pan Li , Eli Chien

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…

Cryptography and Security · Computer Science 2025-10-03 Niloofar Mireshghallah , Tianshi Li

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many studies have shown that FL is vulnerable to membership…

Cryptography and Security · Computer Science 2021-09-14 Hongsheng Hu , Zoran Salcic , Lichao Sun , Gillian Dobbie , Xuyun Zhang

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Cryptography and Security · Computer Science 2020-12-10 Liwei Song , Prateek Mittal

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Cryptography and Security · Computer Science 2026-05-08 Zeyuan Chen , Yihan Ma , Xinyue Shen , Michael Backes , Yang Zhang

In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses conceal the presence of a target sample through strong…

Cryptography and Security · Computer Science 2022-03-03 Ismat Jarin , Birhanu Eshete

Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…

Machine Learning · Computer Science 2020-06-11 Yigitcan Kaya , Sanghyun Hong , Tudor Dumitras

Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM)…

Machine Learning · Computer Science 2025-05-07 Faiz Taleb , Ivan Gazeau , Maryline Laurent

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Machine Learning · Computer Science 2024-11-19 Haonan Duan , Adam Dziedzic , Mohammad Yaghini , Nicolas Papernot , Franziska Boenisch