arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.05786cs.CRcs.AIcs.CL
收藏

AI代理中的证明-护栏以及从其中(不)应信任什么

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

Xisen Jin, Michael Duan, Qin Lin, Aaron Chan, Zhenglun Chen, Junyi Du, Xiang Ren

AI总结:

本文提出proof-of-guardrail系统,通过可信执行环境生成加密证明,确保代理在特定开源护栏后生成响应,同时保护开发者隐私,但指出恶意开发者可能欺骗安全措施的风险。

摘要:

随着AI代理广泛部署为在线服务,用户常依赖开发者关于安全措施的声明,这可能引发安全措施被虚假宣传的威胁。为应对这一威胁,我们提出了proof-of-guardrail系统,使开发者能提供加密证明,证明响应是在特定开源护栏后生成的。为生成证明,开发者需在可信执行环境(TEE)中运行代理和护栏,产生可由用户离线验证的TEE签名证明。我们实现了proof-of-guardrail用于OpenClaw代理,并评估了延迟开销和部署成本。proof-of-guardrail在保持开发者代理隐私的同时确保护栏执行的完整性,但我们也指出恶意开发者可能主动破解护栏的风险。代码和演示视频:https://github.com/SaharaLabsAI/Verifiable-ClawGuard

英文摘要:

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

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。

↑