Large language models (LLMs) are increasingly deployed in privacy-critical and personalization-oriented scenarios, yet the role of context length in shaping privacy leakage and personalization effectiveness remains largely unexplored. We introduce a large-scale benchmark, PAPerBench, to systematically study how increasing context length influences both personalization quality and privacy protection in LLMs. The benchmark comprises approximately 29,000 instances with context lengths ranging from 1K to 256K tokens, yielding a total of 377K evaluation questions. It jointly evaluates personalization performance and privacy risks across diverse scenarios, enabling controlled analysis of long-context model behavior. Extensive evaluations across state-of-the-art LLMs reveal consistent performance degradation in both personalization and privacy as context length increases. We further provide a theoretical analysis of attention dilution under context scaling, explaining this behavior as an inherent limitation of soft attention in fixed-capacity Transformers. The empirical and theoretical findings together suggest a general scaling gap in current models -- long context, less focus. We release the benchmark to support reproducible evaluation and future research on scalable privacy and personalization. Code and data are available at https://github.com/SafeRL-Lab/PAPerBench
PRISP: Privacy-Safe Few-Shot Personalization via Lightweight Adaptation
Department of Electrical and Computer Engineering, Seoul National University(电子与计算机工程系,首尔国立大学);ASRI/INMC/IPAI/AIIS, Seoul National University(ASRI/INMC/IPAI/AIIS,首尔国立大学)
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
Shandong University(山东大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);New York University(纽约大学);Xi'an Jiaotong University(西安交通大学);Australian National University(澳大利亚国立大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Puda: Private User Dataset Agent for User-Sovereign and Privacy-Preserving Personalized AI
Research Institute of Advanced Technology, SoftBank Corp.(软银公司先进科技研究所);Turnt Up Technologies, Inc.(Turnt Up技术公司);TechArts Co., Ltd.(TechArts公司);Acutus Software, Inc.(Acutus软件公司)
A Survey on Foundation Models for Personalized Federated Intelligence
School of Computing, Kyung Hee University(韩国庆熙大学计算机学院);Noakhali Science and Technology University(诺阿克利科学与技术大学);Korea Advanced Institute of Science and Technology(韩国科学技术院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Privacy in Metalearning and Multitask Learning: Modeling and Separations
Rice University(莱斯大学);Hariri Institute for Computing at Boston University(波士顿大学哈里里计算研究所);Boston University(波士顿大学);Northeastern University(东北大学);Simons Institute for the Theory of Computing(西蒙斯理论计算研究所);Khoury College of Computer Sciences, Northeastern University(东北大学库尔计算机科学学院);Google(谷歌)
Department of Computer Science & Engineering, The Ohio State University(计算机科学与工程系,俄亥俄州立大学);Department of Computer Science & Engineering and the Translational Data Analytics Institute (TDAI), The Ohio State University(计算机科学与工程系和转化数据分析研究所(TDAI),俄亥俄州立大学);Google Research, NY(谷歌研究,纽约)
DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents
Sangmyung University(祥明大学);College of Staten Island, The City University of New York(纽约城市大学斯塔滕岛学院);Sookmyung Women’s University(淑明女子大学);Hansung University(汉城大学);Yonsei University(延世大学)