English
Related papers

Related papers: What Does the Server See? Understanding Privacy Le…

200 papers

Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…

Cryptography and Security · Computer Science 2025-11-03 Kathrin Grosse , Nico Ebert

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear.…

Machine Learning · Computer Science 2026-04-27 Xiaoyi Chen , Haoyuan Wang , Siyuan Tang , Sijia Liu , Liya Su , XiaoFeng Wang , Haixu Tang

As deep learning models become larger and more expensive, many practitioners turn to fine-tuning APIs. These web services allow fine-tuning a model between two parties: the client that provides the data, and the server that hosts the model.…

Machine Learning · Computer Science 2024-12-24 Philip Zmushko , Marat Mansurov , Ruslan Svirschevski , Denis Kuznedelev , Max Ryabinin , Aleksandr Beznosikov

Protecting the confidentiality of private data and using it for useful collaboration have long been at odds. Modern cryptography is bridging this gap through rapid growth in secure protocols such as multi-party computation,…

Cryptography and Security · Computer Science 2023-06-12 Maximilian Zinkus , Yinzhi Cao , Matthew Green

The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools. Although this decoupled architecture fosters modularity, it…

Cryptography and Security · Computer Science 2026-02-17 Yunhao Yao , Zhiqiang Wang , Haoran Cheng , Yihang Cheng , Haohua Du , Xiang-Yang Li

Machine learning (ML) has become prominent in applications that directly affect people's quality of life, including in healthcare, justice, and finance. ML models have been found to exhibit discrimination based on sensitive attributes such…

Machine Learning · Computer Science 2022-05-25 Sikha Pentyala , David Melanson , Martine De Cock , Golnoosh Farnadi

The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details,…

Cryptography and Security · Computer Science 2023-10-20 Imdad Ullah , Najm Hassan , Sukhpal Singh Gill , Basem Suleiman , Tariq Ahamed Ahanger , Zawar Shah , Junaid Qadir , Salil S. Kanhere

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Machine Learning · Computer Science 2026-02-10 Yuetian Chen , Kaiyuan Zhang , Yuntao Du , Edoardo Stoppa , Charles Fleming , Ashish Kundu , Bruno Ribeiro , Ninghui Li

Federated learning (FL) has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in…

Machine Learning · Computer Science 2025-06-23 Le Jiang , Liyan Ma , Guang Yang

Federated learning (FL) offers a promising paradigm for collaborative model training while preserving data privacy. However, its susceptibility to gradient inversion attacks poses a significant challenge, necessitating robust privacy…

Cryptography and Security · Computer Science 2025-08-19 Xiaojin Zhang , Mingcong Xu , Yiming Li , Wei Chen , Qiang Yang

Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks showed that private…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Jiahao Lu , Xi Sheryl Zhang , Tianli Zhao , Xiangyu He , Jian Cheng

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Machine Learning · Computer Science 2024-11-19 Haonan Duan , Adam Dziedzic , Mohammad Yaghini , Nicolas Papernot , Franziska Boenisch

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

Machine Learning · Computer Science 2024-09-02 Zhuohang Li , Andrew Lowy , Jing Liu , Toshiaki Koike-Akino , Kieran Parsons , Bradley Malin , Ye Wang

Large Language Models (LLMs) are combined with tools to create powerful LLM agents that provide a wide range of services. Unlike traditional software, LLM agent's behavior is determined at runtime by natural language prompts from either…

Cryptography and Security · Computer Science 2025-04-22 Juhee Kim , Woohyuk Choi , Byoungyoung Lee

Federated Learning (FL), a distributed machine learning paradigm, has been adapted to mitigate privacy concerns for customers. Despite their appeal, there are various inference attacks that can exploit shared-plaintext model updates to…

Cryptography and Security · Computer Science 2022-07-20 Hua Ma , Qun Li , Yifeng Zheng , Zhi Zhang , Xiaoning Liu , Yansong Gao , Said F. Al-Sarawi , Derek Abbott

Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy…

Machine Learning · Computer Science 2025-06-11 Mingyuan Fan , Cen Chen , Chengyu Wang , Xiaodan Li , Wenmeng Zhou

Split learning of deep neural networks (SplitNN) has provided a promising solution to learning jointly for the mutual interest of a guest and a host, which may come from different backgrounds, holding features partitioned vertically.…

Machine Learning · Computer Science 2023-04-20 Yunlong Mao , Zexi Xin , Zhenyu Li , Jue Hong , Qingyou Yang , Sheng Zhong

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT)…

Artificial Intelligence · Computer Science 2025-06-04 Chen Qian , Dongrui Liu , Jie Zhang , Yong Liu , Jing Shao

Machine Learning (ML) has emerged as a core technology to provide learning models to perform complex tasks. Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever increasing. However,…

Machine Learning · Computer Science 2024-03-04 Antoine Boutet , Thomas Lebrun , Jan Aalmoes , Adrien Baud

The rapid development of language models (LMs) brings unprecedented accessibility and usage for both models and users. On the one hand, powerful LMs achieve state-of-the-art performance over numerous downstream NLP tasks. On the other hand,…

Computation and Language · Computer Science 2024-06-04 Haoran Li , Dadi Guo , Donghao Li , Wei Fan , Qi Hu , Xin Liu , Chunkit Chan , Duanyi Yao , Yuan Yao , Yangqiu Song