English
Related papers

Related papers: Blackbox Dataset Inference for LLM

200 papers

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

Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…

Cryptography and Security · Computer Science 2020-12-08 Shagufta Mehnaz , Ninghui Li , Elisa Bertino

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential…

Cryptography and Security · Computer Science 2026-03-23 Toan Tran , Olivera Kotevska , Li Xiong

The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory measures like GDPR and CCPA call for using robust auditing…

Cryptography and Security · Computer Science 2024-06-25 Filippo Galli , Luca Melis , Tommaso Cucinotta

Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, positioning them as catalysts for the next technological…

Cryptography and Security · Computer Science 2025-02-10 Yuke Hu , Zheng Li , Zhihao Liu , Yang Zhang , Zhan Qin , Kui Ren , Chun Chen

As large-scale models such as Large Language Models (LLMs) and Large Multimodal Models (LMMs) see increasing deployment, their privacy risks remain underexplored. Membership Inference Attacks (MIAs), which reveal whether a data point was…

Machine Learning · Computer Science 2025-09-03 Hengyu Wu , Yang Cao

In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…

Computation and Language · Computer Science 2021-06-23 Saeed Mahloujifar , Huseyin A. Inan , Melissa Chase , Esha Ghosh , Marcello Hasegawa

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current…

Machine Learning · Computer Science 2024-06-21 Myeongseob Ko , Feiyang Kang , Weiyan Shi , Ming Jin , Zhou Yu , Ruoxi Jia

Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily…

Cryptography and Security · Computer Science 2026-01-07 Zhenpeng Wu , Jian Lou , Zibin Zheng , Chuan Chen

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

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

In this paper, we introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent, compared to what is revealed by prompting the target model with the training data…

Computation and Language · Computer Science 2025-02-11 Aly M. Kassem , Omar Mahmoud , Niloofar Mireshghallah , Hyunwoo Kim , Yulia Tsvetkov , Yejin Choi , Sherif Saad , Santu Rana

With the widespread application of large language models (LLM), concerns about the privacy leakage of model training data have increasingly become a focus. Membership Inference Attacks (MIAs) have emerged as a critical tool for evaluating…

Robotics · Computer Science 2024-12-24 Zichen Song , Sitan Huang , Zhongfeng Kang

Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical…

Computation and Language · Computer Science 2025-05-29 James Y. Huang , Wenxuan Zhou , Fei Wang , Fred Morstatter , Sheng Zhang , Hoifung Poon , Muhao Chen

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

Large Language Models (LLMs) have shown a high capability in answering questions on a diverse range of topics. However, these models sometimes produce biased, ideologized or incorrect responses, limiting their applications if there is no…

Artificial Intelligence · Computer Science 2026-04-08 Xiaotian Zhou , Di Tang , Xiaofeng Wang , Xiaozhong Liu

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

Cryptography and Security · Computer Science 2020-09-11 Yang Zou , Zhikun Zhang , Michael Backes , Yang Zhang

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Zongyu Wu , Minhua Lin , Zhiwei Zhang , Fali Wang , Xianren Zhang , Xiang Zhang , Suhang Wang