让不同服务安全共享攻击指纹，防提示注入攻击。
BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints
- 用隐私保护技术将可疑提示转为可共享的指纹。
- F1得分0.94，搜索速度比原始嵌入快38倍。
- 适合有合规限制的大型企业部署多模型服务。
大型语言模型在企业服务中的广泛应用带来了严重的安全盲区。组织运营多个处理每日数十亿查询的LLM服务，但监管合规边界禁止这些服务之间共享关于提示注入攻击（当前LLM最高风险）的威胁情报。当某一服务检测到攻击时，相同威胁可能在其他服务中持续数月未被发现，因隐私法规禁止跨合规边界共享用户提示。我们提出BinaryShield，首个可在合规边界间安全共享攻击指纹的隐私保护威胁情报系统。BinaryShield通过独特流程——个人信息脱敏、语义嵌入、二值量化与随机响应机制——将可疑提示转换为保留攻击模式且具备隐私保护能力的指纹。评估显示，BinaryShield实现0.94的F1分数，显著优于隐私保护基线SimHash（0.77），同时实现存储压缩与38倍更快的相似性搜索速度。
原文摘要 · Abstract (English)
The widespread deployment of LLMs across enterprise services has created a critical security blind spot. Organizations operate multiple LLM services handling billions of queries daily, yet regulatory compliance boundaries prevent these services from sharing threat intelligence about prompt injection attacks, the top security risk for LLMs. When an attack is detected in one service, the same threat may persist undetected in others for months, as privacy regulations prohibit sharing user prompts across compliance boundaries. We present BinaryShield, \emph{the first privacy-preserving threat intelligence system that enables secure sharing of attack fingerprints across compliance boundaries.} BinaryShield transforms suspicious prompts through a unique pipeline combining PII redaction, semantic embedding, binary quantization, and randomized response mechanism to potentially generate privacy-preserving fingerprints that preserve attack patterns while providing privacy. Our evaluations demonstrate that BinaryShield achieves an F1-score of 0.94, significantly outperforming SimHash (0.77), the privacy-preserving baseline, while achieving storage reduction and 38x faster similarity search compared to dense embeddings.
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。