PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations· PrivDrift: 在活跃的 LLM 对话中审计用户隐私泄露
Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive information during an active conversation, that information may remain behaviorally recoverable through later prompts even after the dialogue shifts to unrelated topics. We introduce \textbf{PrivDrift}, a benchmark for auditing whether user-disclosed secrets remain recoverable after conversational topic drift and persuasion-based probing. PrivDrift contains 1{,}000 controlled multi-turn dialogues with seeded secrets, content-dense drift turns, and standardized extraction probes. Across three LLMs with extended context windows, dialogue-level hybrid leakage remains substantial, ranging from 38.7\% to 54.6\%, and varies strongly by mod
研究 LLM 在话题转换后的用户隐私泄露问题,并提出 PrivDrift 基准。
- 核心方法
- 通过设计包含预设秘密、话题漂移和标准提取探针的多轮对话,定量评估 LLM 的隐私泄露程度。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 用户在与 LLM 交互时泄露的敏感信息在话题转换后仍可能被恢复,威胁隐私安全。
- 关键实验
- 在三个具有扩展上下文窗口的 LLM 上进行了实验,涵盖 1,000 个多轮对话,结果显示隐私泄露率从 38.7% 到 54.6%。
- 主要贡献
- 提出了 PrivDrift 基准,用于审计 LLM 在话题转换后的隐私泄露情况。
- 意义与局限
- PrivDrift 为评估和改进 LLM 的隐私安全性提供了重要工具,但仅适用于研究特定模型和设置。