arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.29062cs.CRcs.AI
收藏

CivicShield:一种跨领域纵深防御框架,用于保护面向政府的AI聊天机器人免受多轮对抗攻击

CivicShield: A Cross-Domain Defense-in-Depth Framework for Securing Government-Facing AI Chatbots Against Multi-Turn Adversarial Attacks

KrishnaSaiReddy Patil

AI总结:

本文提出CivicShield框架,通过多层防御机制提升政府AI聊天机器人安全性,有效检测多轮对抗攻击,理论分析显示多层防御可将攻击概率降低1-2个数量级。

摘要:

基于大语言模型的政府服务聊天机器人面临关键安全漏洞。多轮对抗攻击对现有防御手段的成功率超过90%,单层防护机制被绕过率相似。我们提出了CivicShield,一种跨领域纵深防御框架,用于保护面向政府的AI聊天机器人。借鉴网络安全、形式验证、生物免疫系统、航空安全和零信任密码学,CivicShield引入了七层防御机制:(1)基于能力的零信任基础,(2)周界输入验证,(3)语义防火墙与意图分类,(4)基于对话状态机的安全不变量,(5)行为异常检测,(6)多模型共识验证,以及(7)逐步的人工介入升级。我们提出了涵盖8种多轮攻击类型的正式威胁模型,将框架映射到NIST SP 800-53控制措施的14种类型,并通过消融分析进行评估。理论分析显示,多层防御将攻击概率降低1-2个数量级,相较于单层方法。在1,436种场景中进行模拟,包括HarmBench(416)、JailbreakBench(200)和XSTest(450),实现了72.9%的综合检测率[69.5-76.0%置信区间],在逐步响应后有效误报率仅为2.9%,同时保持对多轮渐进和慢漂攻击的100%检测。在真实基准与作者生成场景之间的诚实下降(HarmBench上71.2% vs 76.7%,JailbreakBench上47.0% vs 70.0%)验证了独立评估的重要性。CivicShield填补了AI安全、政府合规和实际部署交集的开放空白。

英文摘要:

LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current defenses, and single-layer guardrails are bypassed with similar rates. We present CivicShield, a cross-domain defense-in-depth framework for government-facing AI chatbots. Drawing on network security, formal verification, biological immune systems, aviation safety, and zero-trust cryptography, CivicShield introduces seven defense layers: (1) zero-trust foundation with capability-based access control, (2) perimeter input validation, (3) semantic firewall with intent classification, (4) conversation state machine with safety invariants, (5) behavioral anomaly detection, (6) multi-model consensus verification, and (7) graduated human-in-the-loop escalation. We present a formal threat model covering 8 multi-turn attack families, map the framework to NIST SP 800-53 controls across 14 families, and evaluate using ablation analysis. Theoretical analysis shows layered defenses reduce attack probability by 1-2 orders of magnitude versus single-layer approaches. Simulation against 1,436 scenarios including HarmBench (416), JailbreakBench (200), and XSTest (450) achieves 72.9% combined detection [69.5-76.0% CI] with 2.9% effective false positive rate after graduated response, while maintaining 100% detection of multi-turn crescendo and slow-drift attacks. The honest drop on real benchmarks versus author-generated scenarios (71.2% vs 76.7% on HarmBench, 47.0% vs 70.0% on JailbreakBench) validates independent evaluation importance. CivicShield addresses an open gap at the intersection of AI safety, government compliance, and practical deployment.

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。

↑