English
Related papers

Related papers: ReCaLL: Membership Inference via Relative Conditio…

200 papers

Large language models (LLMs) are increasingly trained on tabular data, which, unlike unstructured text, often contains personally identifiable information (PII) in a highly structured and explicit format. As a result, privacy risks arise,…

Cryptography and Security · Computer Science 2025-07-24 Eyal German , Sagiv Antebi , Daniel Samira , Asaf Shabtai , Yuval Elovici

Membership inference attacks (MIAs) have become the standard tool for evaluating privacy leakage in machine learning (ML). Among them, the Likelihood-Ratio Attack (LiRA) is widely regarded as the state of the art when sufficient shadow…

Cryptography and Security · Computer Science 2026-03-10 Najeeb Jebreel , Mona Khalil , David Sánchez , Josep Domingo-Ferrer

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

Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ…

Cryptography and Security · Computer Science 2026-05-11 Yuefeng Peng , Mingzhe Li , Kejing Xia , Renhao Zhang , Amir Houmansadr

Recent work shows membership inference attacks (MIAs) on large language models (LLMs) produce inconclusive results, partly due to difficulties in creating non-member datasets without temporal shifts. While researchers have turned to…

Computation and Language · Computer Science 2025-01-22 Ali Naseh , Niloofar Mireshghallah

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

Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provide a principled framework for auditing these risks, yet…

Computation and Language · Computer Science 2026-04-14 David Ilić , David Stanojević , Kostadin Cvejoski

We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-inference attacks even when the service provider and users are…

Cryptography and Security · Computer Science 2026-05-07 Tejas Kulkarni , Antti Koskela , Laith Zumot

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have…

Computation and Language · Computer Science 2024-12-30 Wenjie Fu , Huandong Wang , Chen Gao , Guanghua Liu , Yong Li , Tao Jiang

Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping user behavior and decision-making, highlighting their…

Information Retrieval · Computer Science 2026-01-09 Jiajie He , Xintong Chen , Xinyang Fang , Min-Chun Chen , Yuechun Gu , Keke Chen

In recent years, Large Language Models (LLMs) have demonstrated an impressive ability to encode knowledge during pre-training on large text corpora. They can leverage this knowledge for downstream tasks like question answering (QA), even in…

Computation and Language · Computer Science 2024-06-11 Juraj Vladika , Phillip Schneider , Florian Matthes

In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the…

Information Theory · Computer Science 2025-06-10 Meiyi Zhu , Caili Guo , Chunyan Feng , Osvaldo Simeone

Membership inference attacks aim to detect if a particular data point was used in training a model. We design a novel statistical test to perform robust membership inference attacks (RMIA) with low computational overhead. We achieve this by…

Machine Learning · Statistics 2024-06-13 Sajjad Zarifzadeh , Philippe Liu , Reza Shokri

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

Cryptography and Security · Computer Science 2025-11-24 Mona Khalil , Alberto Blanco-Justicia , Najeeb Jebreel , Josep Domingo-Ferrer

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

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

Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of limited resources and privacy concerns. Despite data localization, shared gradients can…

Machine Learning · Computer Science 2026-04-24 Guilin Deng , Silong Chen , Yuchuan Luo , Yi Liu , Songlei Wang , Zhiping Cai , Lin Liu , Xiaohua Jia , Shaojing Fu

Large language models (LLMs) are trained on massive web-scale corpora, raising growing concerns about privacy and copyright. Membership inference attacks (MIAs) aim to determine whether a given example was used during training. Existing LLM…

Machine Learning · Computer Science 2026-04-02 Ravi Ranjan , Utkarsh Grover , Xiaomin Lin , Agoritsa Polyzou

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing genuine memorization of training data from…

Machine Learning · Computer Science 2026-02-24 Trishita Tiwari , Ari Trachtenberg , G. Edward Suh

This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal…

Computation and Language · Computer Science 2025-10-13 Tao Feng , Lizhen Qu , Niket Tandon , Zhuang Li , Xiaoxi Kang , Gholamreza Haffari