PrivScope:面向混合代理系统的任务范围披露控制
PrivScope: Task-scoped Disclosure Control for Hybrid Agentic Systems
AI总结:
本文提出PrivScope,一种在本地与云语言模型之间实施任务范围披露控制的可信本地负载管理者,旨在防止在混合代理系统中因任务无关上下文、先前工作流残留信息和过于具体的敏感细节导致的过度披露问题。
摘要:
混合本地-云代理在将能力密集型子任务委托给云语言模型(CLM)之前,会利用持久的工作状态上下文来丰富用户请求。尽管这种增强可以提高任务成功率,但也暴露了云绑定负载中的不必要的信息,包括任务无关的上下文、先前工作流的残留信息以及过于具体的敏感细节,导致过度披露。现有解决方案要么将工作流隔离以限制跨工作流泄漏,要么应用通用目的的清理方法,但这些方法无法在LC组装的负载范围内进行推理。我们提出PrivScope,一种可信的本地负载管理者,它在本地-CLM边界实施任务范围披露控制,而无需对云端进行更改。其关键思想是:敏感信息应仅在需要完成委托子任务时才传送到云,并且以最不透露的形式传递,同时保持实用性。PrivScope从组装的负载中提取披露单元,并在本地保留直接标识符和账户关联值。其余单元通过云必要性控制,确定实际上需要什么;必须传送到云的单元会被抽象为最不具体的表示,足以完成任务。在100个医疗预约工作流上跨三个商业CLM测试中,PrivScope消除了资料泄漏(0.0% vs. 17.7%),将攻击者再识别率减少了一半以上(23.1% vs. 64.3%),并在每个测试的CLM上实现了最高的候选召回率,同时在GPT-4o-mini和Gemini 2.5 Flash上保持任务成功率接近未保护基线。在五种本地后端和商用硬件上,收益持续存在,仅增加了几秒钟的本地延迟。
英文摘要:
Hybrid local--cloud agents enrich user requests with context from persistent working state before delegating capability-intensive subtasks to a cloud language model (CLM). While this enrichment can improve task success, it also exposes unnecessary information in the cloud-bound payload, including task-irrelevant context, carryover from prior workflows, and overly specific sensitive details, resulting in \emph{over-disclosure}. Existing solutions either isolate workflows to limit cross-workflow leakage or apply general-purpose sanitization that does not reason over LC-assembled payload scope. We present \textsc{PrivScope}, a trusted on-device payload governor that enforces \emph{task-scoped disclosure} at the local--CLM boundary, without requiring cloud-side changes. Its key idea: sensitive information should reach the cloud only when required for the delegated subtask, and then only in the least revealing form preserving utility. \textsc{PrivScope} extracts disclosure units from the assembled payload and keeps direct identifiers and account-linked values on device. The remaining units pass through cloud-necessity control, which determines what is actually needed; units that must reach the cloud are abstracted to the least-specific representation sufficient for the task. On 100 medical-booking workflows across three commercial CLMs, \textsc{PrivScope} eliminates profile leakage (0.0\% vs.\ 17.7\%), more than halves attacker re-identification (23.1\% vs.\ 64.3\%), and achieves the highest candidate recall on every CLM tested while preserving task success close to the unprotected baseline on GPT-4o-mini and Gemini 2.5 Flash. Gains hold across five local backbones and add only seconds of on-device latency on commodity hardware.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。