English
Related papers

Related papers: Membership Inference Attacks Against Vision-Langua…

200 papers

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

Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…

Machine Learning · Computer Science 2025-06-03 Toan Tran , Ruixuan Liu , Li Xiong

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

Membership inference attack (MIA) has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's…

Cryptography and Security · Computer Science 2025-06-04 Jing Xue , Zhishen Sun , Haishan Ye , Luo Luo , Xiangyu Chang , Ivor Tsang , Guang Dai

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Xiaosen Wang , Shaokang Wang , Zhijin Ge , Yuyang Luo , Shudong Zhang

With large language models (LLMs) poised to become embedded in our daily lives, questions are starting to be raised about the data they learned from. These questions range from potential bias or misinformation LLMs could retain from their…

Computation and Language · Computer Science 2024-07-17 Matthieu Meeus , Shubham Jain , Marek Rei , Yves-Alexandre de Montjoye

Membership inference attacks (MIAs) aim to determine whether a data sample was included in a machine learning (ML) model's training set and have become the de facto standard for measuring privacy leakages in ML. We propose an evaluation…

Cryptography and Security · Computer Science 2026-03-25 Najeeb Jebreel , David Sánchez , Josep Domingo-Ferrer

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Machine Learning · Computer Science 2026-01-13 Ziyao Cui , Minxing Zhang , Jian Pei

The rapid scaling of large language models (LLMs) has raised concerns about the transparency and fair use of the data used in their pretraining. Detecting such content is challenging due to the scale of the data and limited exposure of each…

Computation and Language · Computer Science 2025-05-26 Roy Xie , Junlin Wang , Ruomin Huang , Minxing Zhang , Rong Ge , Jian Pei , Neil Zhenqiang Gong , Bhuwan Dhingra

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

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

Cryptography and Security · Computer Science 2025-06-06 Lorenzo Rossi , Michael Aerni , Jie Zhang , Florian Tramèr

The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…

Machine Learning · Computer Science 2024-05-22 Jamie Hayes , Ilia Shumailov , Eleni Triantafillou , Amr Khalifa , Nicolas Papernot

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and…

Cryptography and Security · Computer Science 2026-01-30 Puwei Lian , Yujun Cai , Songze Li , Bingkun Bao

As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the…

Cryptography and Security · Computer Science 2025-10-22 Alexander Nemecek , Zebin Yun , Zahra Rahmani , Yaniv Harel , Vipin Chaudhary , Mahmood Sharif , Erman Ayday

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…

Cryptography and Security · Computer Science 2026-05-12 Hiromu Takahashi , Shotaro Ishihara

Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…

Cryptography and Security · Computer Science 2026-05-05 Karima Makhlouf , Lamiaa Basyoni , Syed Khaderi , Gabriel Marquez , Peter Sotomango , Mahmoud Awawdah , Sami Zhioua

Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a specific data sample was included in the training set. Although federated learning (FL) is…

Cryptography and Security · Computer Science 2026-01-27 Mohammad Zare , Pirooz Shamsinejadbabaki

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

Cryptography and Security · Computer Science 2026-05-27 Qilin Liao , Anamika Lochab , Ruqi Zhang

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

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Simone Caldarella , Massimiliano Mancini , Elisa Ricci , Rahaf Aljundi