English
Related papers

Related papers: Membership Inference Attacks on Discrete Diffusion…

200 papers

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

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

Cryptography and Security · Computer Science 2025-12-17 Yihan Liao , Jacky Keung , Xiaoxue Ma , Jingyu Zhang , Yicheng Sun

Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Ouxiang Li , Yanbin Hao , Zhicai Wang , Bin Zhu , Shuo Wang , Zaixi Zhang , Fuli Feng

With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model developers may misuse the unauthorized data to train…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Qiao Li , Xiaomeng Fu , Xi Wang , Jin Liu , Xingyu Gao , Jiao Dai , Jizhong Han

Recently, diffusion models have achieved remarkable success in generating tasks, including image and audio generation. However, like other generative models, diffusion models are prone to privacy issues. In this paper, we propose an…

Sound · Computer Science 2023-10-10 Fei Kong , Jinhao Duan , RuiPeng Ma , Hengtao Shen , Xiaofeng Zhu , Xiaoshuang Shi , Kaidi Xu

Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent…

Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is to utilize differential privacy (DP) during model training…

Cryptography and Security · Computer Science 2022-04-14 Saeed Mahloujifar , Alexandre Sablayrolles , Graham Cormode , Somesh Jha

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training…

Cryptography and Security · Computer Science 2026-01-13 Yuntao Du , Yuetian Chen , Hanshen Xiao , Bruno Ribeiro , Ninghui Li

While pre-trained Transformer models achieve high accuracy on in-domain sentiment classification, they frequently experience severe performance degradation when transferring to out-of-domain data. We hypothesize that this generalization gap…

Machine Learning · Computer Science 2026-05-06 Shubham Harkare , Arvind Yogesh Suresh Babu , Yash Kulkarni

Recent advances in generative artificial intelligence applications have raised new data security concerns. This paper focuses on defending diffusion models against membership inference attacks. This type of attack occurs when the attacker…

Machine Learning · Computer Science 2026-05-08 Benjamin Sterling , Yousef El-Laham , Mónica F. Bugallo

Membership inference attacks allow a malicious entity to predict whether a sample is used during training of a victim model or not. State-of-the-art membership inference attacks have shown to achieve good accuracy which poses a great…

Machine Learning · Computer Science 2022-03-07 Shahbaz Rezaei , Xin Liu

Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs) aim at determining if a data point was part of the model's training set. Prior MIAs that are built for classification models fail at LLMs, due to ignoring the…

Computation and Language · Computer Science 2025-09-17 Hongyan Chang , Ali Shahin Shamsabadi , Kleomenis Katevas , Hamed Haddadi , Reza Shokri

Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLMs generate text by…

Computation and Language · Computer Science 2026-05-19 Georu Lee , Seungwon Jeong , Hoki Kim , Jinseong Park , Woojin Lee

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

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with…

Computation and Language · Computer Science 2024-11-19 Zixiong Wang , Gaoyang Liu , Yang Yang , Chen Wang

Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attacks require training numerous, often computationally expensive, reference models, limiting…

Machine Learning · Computer Science 2025-10-23 Euodia Dodd , Nataša Krčo , Igor Shilov , Yves-Alexandre de Montjoye

Large Language Models (LLMs) have seen widespread adoption due to their remarkable natural language capabilities. However, when deploying them in real-world settings, it is important to align LLMs to generate texts according to acceptable…

Artificial Intelligence · Computer Science 2025-04-29 Qizhang Feng , Siva Rajesh Kasa , Santhosh Kumar Kasa , Hyokun Yun , Choon Hui Teo , Sravan Babu Bodapati

Autoregressive language models (ARMs) suffer from the reversal curse: after learning ''$A$ is $B$,'' they often fail on the reverse query ''$B$ is $A$.'' Masked diffusion language models (MDMs) exhibit this failure in a much weaker form,…

Artificial Intelligence · Computer Science 2026-05-13 Moongyu Jeon , Sangwoo Shin , BumJun Kim , Kyelim Lee , Albert No

Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training…

Cryptography and Security · Computer Science 2026-05-28 Kai Chen , Yan Pang , Tianhao Wang

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to…

Cryptography and Security · Computer Science 2025-02-27 Yu He , Boheng Li , Liu Liu , Zhongjie Ba , Wei Dong , Yiming Li , Zhan Qin , Kui Ren , Chun Chen