让AI安全承诺可验证，防止开发者虚假宣传安全措施。
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
- 在可信执行环境运行守护程序，生成可离线验证的加密证明。
- 实测对OpenClaw代理延迟影响小于5%，部署成本可控。
- 适合关注AI安全透明度的开发者与监管机构使用。
随着AI代理作为在线服务广泛部署，用户往往依赖开发者声称的安全保障，这带来了虚假宣传安全措施的风险。为此，我们提出「证明-守卫」机制，使开发者能够提供加密证明，证明响应是在特定开源守卫程序之后生成的。开发者将代理和守卫程序在可信执行环境（TEE）中运行，由TEE生成签名的执行证明，任何用户均可离线验证。我们为OpenClaw代理实现了该系统，并评估了延迟开销与部署成本。该方案确保了守卫程序执行的完整性，同时保护开发者代理隐私；但我们也指出，恶意开发者仍可能主动绕过守卫，造成安全欺骗风险。代码与演示视频见：https://github.com/SaharaLabsAI/Verifiable-ClawGuard。
原文摘要 · Abstract (English)
As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures are falsely advertised. To address the threat, we propose proof-of-guardrail, a system that enables developers to provide cryptographic proof that a response is generated after a specific open-source guardrail. To generate proof, the developer runs the agent and guardrail inside a Trusted Execution Environment (TEE), which produces a TEE-signed attestation of guardrail code execution verifiable by any user offline. We implement proof-of-guardrail for OpenClaw agents and evaluate latency overhead and deployment cost. Proof-of-guardrail ensures integrity of guardrail execution while keeping the developer's agent private, but we also highlight a risk of deception about safety, for example, when malicious developers actively jailbreak the guardrail. Code and demo video: https://github.com/SaharaLabsAI/Verifiable-ClawGuard
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。