arXiv cs.AI· Robin Staab, Tom Wollschl\"ager, Vahab Mirrokni, Reza Shokri·· 1 天前AI 评分44
PrivacyFlow：通过信息流分析与后果感知风险管理保障 AI 智能体隐私
PrivacyFlow: Privacy in AI Agents through Information Flow Analysis and Consequence-Aware Risk Management
AI 导读
PrivacyFlow 将隐私规划（System 2）与任务执行（System 1）分离，把每次数据共享决策当作结构化风险管理问题，在六个模型上显著减少步骤级隐私失败，并将无隐私违规的完整任务序列占比提升 22–55 个百分点。
正文 · 原文
Abstract:Autonomous LLM agents executing multi-step workflows over personal data often misalign with user privacy expectations and leak sensitive, out-of-context information. Although Contextual Integrity (CI) formalizes this problem, existing benchmarks and defenses rarely operationalize CI for realistic multi-step task sequences in evolving environments. In this work, we first introduce agentic PrivacyBench, a benchmark of 5873 tasks in 986 task sequences with dynamic environment updates and CI-grounded allow-sets for sensitive information. We also introduce PrivacyFlow, a defense that separates deliberative privacy planning (System 2) from task execution (System 1), treating each sharing decision as a structured risk-management problem. Before execution, PrivacyFlow traces the provenance and purpose of each planned data flow, models recipient background knowledge, and simulates what external actors could infer. This allows us to model the downstream consequences of disclosure, including inference attacks and context-dependent harms. It then weighs the remaining disclosure risk against task utility and executes a minimized plan, blocks it, or consults the user. Across six models, PrivacyFlow significantly reduces step-level privacy failures and raises the share of completed task sequences without a detected privacy violation by 22--55 percentage points. We further highlight a new privacy--utility--autonomy tradeoff: allowing PrivacyFlow to proactively prompt the user in case of uncertainty can increase authorized task completion at the cost of shifting decision effort back to the user. Our results suggest that proactive CI reasoning can substantially improve agentic privacy and motivate further study of this tradeoff.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.40714 [cs.CR] |
| (or arXiv:2610.40714v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40714 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Reza Shokri [view email]
[v1]
Thu, 29 Oct 2026 01:54:36 UTC (152 KB)
来源：arXiv cs.AI · arxiv.org