Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharing

2025-09-26 · Bingcan Guo, Eryue Xu, Zhiping Zhang, Tianshi Li arxiv

Aligning AI systems with human privacy preferences requires understanding individuals' nuanced disclosure behaviors beyond general norms. Yet eliciting such boundaries remains challenging due to the context-dependent nature of privacy decisions and the complex trade-offs involved. We present an AI-powered elicitation approach that probes individuals' privacy boundaries through a discriminative task. We conducted a between-subjects study that systematically varied communication roles and delegation conditions, resulting in 1,681 boundary specifications from 169 participants for 61 scenarios. We examined how these contextual factors and individual differences influence the boundary specification. Quantitative results show that communication roles influence individuals' acceptance of detailed and identifiable disclosure, AI delegation and individuals' need for privacy heighten sensitivity to disclosed identifiers, and AI delegation results in less consensus across individuals. Our findings highlight the importance of situating privacy preference elicitation within real-world data flows. We advocate using nuanced privacy boundaries as an alignment goal for future AI systems.

📄 PDF Abstract BibTeX arXiv:2509.21712

Code (0)

등록된 구현이 없습니다.

CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment

2026-08-10 · Bingcan Guo, Eryue Xu, Jijie Zhou, Zhiping Zhang 외 arxiv

Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms. However, a gap remains in eliciting such nuanced preferences to eva…

AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows

2026-03-05 · Ivoline C. Ngong, Keerthiram Murugesan, Swanand Kadhe, Justin D. Weisz 외 arxiv

Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focused on the input and output boundaries, bu…

NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries

2026-06-29 · Aydin Javadov, Shyngys Aitkazinov, Tobias Hoesli, Florian von Wangenheim 외 arxiv

A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training primarily amplifying rather than introducing them. However, this evidence…

Arithmetic Reasoning Code Generation Decision Making

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

2026-04-01 · Prince Zizhuang Wang, Shuli Jiang arxiv

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple…

Prompt Engineering

Personalized Privacy Control in LLMs via Attention Head Intervention

2026-08-21 · Junseok Kim, Nakyeong Yang, Kyomin Jung arxiv

The rise of agentic AI enables LLMs to access diverse user data, raising critical privacy concerns. Prior work on contextual privacy studies whether LLMs regulate information disclosure according to context-dependent nor…