让AI代理内生隐私保护，自动避免敏感信息泄露。
PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training
- 通过多智能体偏好训练，将隐私偏好嵌入模型生成行为
- 隐私泄露率降低最高达12.32%，且帮助性基本不变
- 适合需要高隐私安全的个性化AI应用
大型语言模型（LLM）代理在涉及敏感上下文信息的个性化任务中日益普及，但其行为可能因上下文隐私的隐含性而引发隐私泄露。现有方法依赖外部、运行时干预，存在脆弱、场景特定且扩大隐私攻击面的问题。我们提出PrivAct，一种将上下文隐私保护内化至模型生成行为的多智能体学习框架，使代理行为符合隐私要求。通过为每个代理嵌入隐私偏好，PrivAct提升系统整体上下文完整性，并实现更优的隐私-帮助性权衡。在多个LLM基线和基准上的实验表明，该方法在保持相近帮助性的同时，隐私泄露率最高降低12.32%，并具备零样本泛化与多种多智能体拓扑下的鲁棒性。代码已开源：https://github.com/chengyh23/PrivAct。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy. Existing approaches rely on external, inference-time interventions which are brittle, scenario-specific, and may expand the privacy attack surface. We propose PrivAct, a contextual privacy-aware multi-agent learning framework that internalizes contextual privacy preservation directly into models' generation behavior for privacy-compliant agentic actions. By embedding privacy preferences into each agent, PrivAct enhances system-wide contextual integrity while achieving a more favorable privacy-helpfulness tradeoff. Experiments across multiple LLM backbones and benchmarks demonstrate consistent improvements in contextual privacy preservation, reducing leakage rates by up to 12.32% while maintaining comparable helpfulness, as well as zero-shot generalization and robustness across diverse multi-agent topologies. Code is available at https://github.com/chengyh23/PrivAct.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。