English
Related papers

Related papers: RelaxLoss: Defending Membership Inference Attacks …

200 papers

A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or…

Cryptography and Security · Computer Science 2025-09-09 Yuntao Du , Jiacheng Li , Yuetian Chen , Kaiyuan Zhang , Zhizhen Yuan , Hanshen Xiao , Bruno Ribeiro , Ninghui Li

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

Large Reasoning Models (LRMs) have rapidly gained prominence for their strong performance in solving complex tasks. Many modern black-box LRMs expose the intermediate reasoning traces through APIs to improve transparency (e.g., Gemini-2.5…

Cryptography and Security · Computer Science 2026-01-21 Ruihan Hu , Yu-Ming Shang , Wei Luo , Ye Tao , Xi Zhang

Membership Inference Attacks have emerged as a dominant method for empirically measuring privacy leakage from machine learning models. Here, privacy is measured by the {\em{advantage}} or gap between a score or a function computed on the…

Machine Learning · Computer Science 2024-05-27 Ruihan Wu , Pengrun Huang , Kamalika Chaudhuri

Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning…

Machine Learning · Computer Science 2026-05-12 Joshua Ward , Bochao Gu , Chi-Hua Wang , Guang Cheng

Machine learning (ML) models have significantly grown in complexity and utility, driving advances across multiple domains. However, substantial computational resources and specialized expertise have historically restricted their wide…

Cryptography and Security · Computer Science 2025-08-28 Kaixiang Zhao , Lincan Li , Kaize Ding , Neil Zhenqiang Gong , Yue Zhao , Yushun Dong

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data,…

Cryptography and Security · Computer Science 2025-11-05 Jinhua Yin , Peiru Yang , Chen Yang , Huili Wang , Zhiyang Hu , Shangguang Wang , Yongfeng Huang , Tao Qi

Machine learning models can inadvertently expose confidential properties of their training data, making them vulnerable to membership inference attacks (MIA). While numerous evaluation methods exist, many require computationally expensive…

Machine Learning · Computer Science 2026-02-04 Richard J. Preen , Jim Smith

The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous…

Computation and Language · Computer Science 2024-12-19 Bowen Chen , Namgi Han , Yusuke Miyao

In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 David Amebley , Sayanton Dibbo

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…

Cryptography and Security · Computer Science 2019-02-04 Stacey Truex , Ling Liu , Mehmet Emre Gursoy , Lei Yu , Wenqi Wei

A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training data. Most MI research focuses on the case of a single…

Machine Learning · Computer Science 2022-05-16 Matthew Jagielski , Stanley Wu , Alina Oprea , Jonathan Ullman , Roxana Geambasu

Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently, understanding training-data leakage in these systems is increasingly critical. Log-probability-based…

Cryptography and Security · Computer Science 2026-05-22 Ziyi Tong , Feifei Sun , Le Minh Nguyen

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

Cryptography and Security · Computer Science 2022-12-05 Tomas Chobola , Dmitrii Usynin , Georgios Kaissis

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their…

Cryptography and Security · Computer Science 2025-06-09 Ruining Sun , Hongsheng Hu , Wei Luo , Zhaoxi Zhang , Yanjun Zhang , Haizhuan Yuan , Leo Yu Zhang

Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets…

Machine Learning · Computer Science 2024-10-07 Chumeng Liang , Jiaxuan You

Membership inference attacks (MIAs) infer whether a specific data record is used for target model training. MIAs have provoked many discussions in the information security community since they give rise to severe data privacy issues,…

Artificial Intelligence · Computer Science 2022-03-02 Yu Wang , Lifu Huang , Philip S. Yu , Lichao Sun

Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through…

Machine Learning · Computer Science 2026-05-26 Joonas Jälkö , Gauri Pradhan , Ossi Räisä , Antti Honkela

Diffusion models have demonstrated remarkable capabilities in image synthesis, but their recently proven vulnerability to Membership Inference Attacks (MIAs) poses a critical privacy concern. This paper introduces two novel and efficient…

Machine Learning · Computer Science 2024-10-23 Bao Q. Tran , Viet Nguyen , Anh Tran , Toan Tran

While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary…

Machine Learning · Computer Science 2025-05-29 Huan Tian , Guangsheng Zhang , Bo Liu , Tianqing Zhu , Ming Ding , Wanlei Zhou