English
Related papers

Related papers: In-Context Probing for Membership Inference in Fin…

200 papers

Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was…

Cryptography and Security · Computer Science 2025-12-02 Bram van Dartel , Marc Damie , Florian Hahn

Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely…

Machine Learning · Computer Science 2025-06-09 Cheng-Long Wang , Qi Li , Zihang Xiang , Yinzhi Cao , Di Wang

Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users' membership…

Cryptography and Security · Computer Science 2024-05-14 Xiaoxiao Chi , Xuyun Zhang , Yan Wang , Lianyong Qi , Amin Beheshti , Xiaolong Xu , Kim-Kwang Raymond Choo , Shuo Wang , Hongsheng Hu

Most membership inference attacks (MIAs) against Large Language Models (LLMs) rely on global signals, like average loss, to identify training data. This approach, however, dilutes the subtle, localized signals of memorization, reducing…

Computation and Language · Computer Science 2026-03-09 Yuetian Chen , Yuntao Du , Kaiyuan Zhang , Ashish Kundu , Charles Fleming , Bruno Ribeiro , Ninghui Li

Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages,…

Cryptography and Security · Computer Science 2024-07-23 Hao Li , Zheng Li , Siyuan Wu , Chengrui Hu , Yutong Ye , Min Zhang , Dengguo Feng , Yang Zhang

Membership inference attacks (MIAs) aim to determine whether a specific data point was part of a model's training set, serving as effective tools for evaluating privacy leakage of vision models. However, existing MIAs implicitly assume…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Ruize Gao , Kaiwen Zhou , Yongqiang Chen , Feng Liu

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

All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the designer's intuition. We introduce the first transferable…

Computation and Language · Computer Science 2026-04-06 David Ilić , Kostadin Cvejoski , David Stanojević , Evgeny Grigorenko

Membership inference attacks (MIAs) test whether a specific audio clip was used to train a model, making them a key tool for auditing generative music models for copyright compliance. However, loss-based signals (e.g., reconstruction error)…

Sound · Computer Science 2026-02-03 Yuxuan Liu , Peihong Zhang , Rui Sang , Zhixin Li , Yizhou Tan , Yiqiang Cai , Shengchen Li

This paper extends the Classification Error Gauge (x-CEG) framework, originally developed for measuring the privacy-utility trade-off in tabular datasets, to privacy auditing of Large Language Models (LLMs). We propose LLM-CEG, a systematic…

Cryptography and Security · Computer Science 2026-04-28 Kato Mivule

As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the development of various fine-tuning methods. However, the privacy…

Computation and Language · Computer Science 2025-07-02 Jie Hou , Chuxiong Wu , Lannan Luo , Qiang Zeng

Large language models (LLMs) have become essential tools for digital task assistance. Their training relies heavily on the collection of vast amounts of data, which may include copyright-protected or sensitive information. Recent studies on…

Cryptography and Security · Computer Science 2025-09-22 Sagiv Antebi , Edan Habler , Asaf Shabtai , Yuval Elovici

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

Cryptography and Security · Computer Science 2025-12-09 Ruikai Zhou , Kang Yang , Xun Chen , Wendy Hui Wang , Guanhong Tao , Jun Xu

Federated Learning (FL) is a promising approach for training machine learning models on decentralized data while preserving privacy. However, privacy risks, particularly Membership Inference Attacks (MIAs), which aim to determine whether a…

Machine Learning · Computer Science 2025-03-28 Gongxi Zhu , Donghao Li , Hanlin Gu , Yuan Yao , Lixin Fan , Yuxing Han

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…

Machine Learning · Computer Science 2022-11-07 Fatemehsadat Mireshghallah , Kartik Goyal , Archit Uniyal , Taylor Berg-Kirkpatrick , Reza Shokri

Large pretrained language models (LLMs) have shown surprising In-Context Learning (ICL) ability. An important application in deploying large language models is to augment LLMs with a private database for some specific task. The main problem…

Cryptography and Security · Computer Science 2024-05-09 Chunyan Zheng , Keke Sun , Wenhao Zhao , Haibo Zhou , Lixin Jiang , Shaoyang Song , Chunlai Zhou

Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…

Cryptography and Security · Computer Science 2025-01-22 Cong Wu , Jing Chen , Qianru Fang , Kun He , Ziming Zhao , Hao Ren , Guowen Xu , Yang Liu , Yang Xiang

Given the rising popularity of AI-generated art and the associated copyright concerns, identifying whether an artwork was used to train a diffusion model is an important research topic. The work approaches this problem from the membership…

Cryptography and Security · Computer Science 2025-08-14 Jingwei Li , Jing Dong , Tianxing He , Jingzhao Zhang

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment…

Cryptography and Security · Computer Science 2025-05-19 Yidan Wang , Yanan Cao , Yubing Ren , Fang Fang , Zheng Lin , Binxing Fang

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their…

Machine Learning · Computer Science 2024-10-18 Jie Ren , Kangrui Chen , Chen Chen , Vikash Sehwag , Yue Xing , Jiliang Tang , Lingjuan Lyu