arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.21063cs.CRcs.AI
收藏

究竟批准什么?智能体升级授权的效果绑定与可信渲染

Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization

SportsVision AI

Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill

AI总结:

该研究针对智能体升级授权的批准路径,定义12种攻击并测试现有方案,提出ASU网关防御方案,经实验验证其能有效降低多种攻击成功率,提升自动批准器的攻击捕获率。

摘要:

AI智能体在发送资金、删除文件或向外部人员发送电子邮件前会暂停以获取批准,而这种批准通常被视为第二因素。我们认为,只有当破坏智能体无法生成该批准且批准明确指定其批准的内容时,它才是第二因素,我们对这两个条件进行了测试。我们定义了12种针对批准路径的攻击,包括诱饵收件人、金额取消、卡片填充、标签欺骗、注册 squatting( squatting 保留原词)和阈值拆分,并针对智能体支付协议(AP2)、微软的动作绑定批准设计以及模型上下文协议(MCP)诱导运行这些攻击。对10个智能体运行时的审计发现,没有第三方可验证的批准记录,在可测量的情况下没有流量限制,且在8个具有可测量绑定的运行时中,有4个在批准后发生了参数变化。作为参考防御,我们构建了ASU(智能体升级),这是一个从规范效果描述符渲染批准卡片的网关,具有用户手机上的密钥对其摘要进行签名,且仅执行存储的调用。Tamarin在三个所述假设下证明了其绑定性、一次性和密钥级不可否认性属性(53个引理)。在27108次脚本试验和609个AgentDojo攻击对中,ASU阻止了替换、重放和授权延长,且可信卡片将伪造叙述攻击的成功率从0.54降至0.03。使用15个当前语言模型作为自动批准器,可信卡片将攻击捕获率从0.30提高到0.98,代价是拒绝了16%的无害近误,主要是由于我们的刺激中的占位符伪影。在这些实验中,第二个设备相对于可信的主机上确认没有增加可测量的效果,针对建模的批准器,流量攻击仍以0.45至0.60的成功率成功,且批准无法阻止策略已允许的效果。代码、数据和证明:this https URL

英文摘要:

AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually treated as a second factor. We argue it is one only when compromising the agent cannot produce it and when it names exactly what it approves, and we test both conditions. We define twelve attacks on the approval path, including decoy recipients, amount cancellation, card padding, label spoofing, enrollment squatting and threshold splitting, and run them against the Agent Payments Protocol (AP2), the Microsoft action-bound approval design and Model Context Protocol (MCP) elicitation. An audit of ten agent runtimes finds no third-party verifiable approval record, no flood limits where measurable, and post-approval argument changes in four of eight runtimes with measurable binding. As a reference defense we build ASU (Agent Step-Up), a gateway that renders the approval card from a canonical effect descriptor, has a passkey on the phone of the user sign its digest, and executes only the stored call. Tamarin proves its binding, single-use and key-level non-repudiation properties under three stated hypotheses (53 lemmas). Across 27,108 scripted trials and 609 AgentDojo attack pairs, ASU stops substitution, replay and grant stretching, and the trusted card cuts forged-narration attack success from 0.54 to 0.03. With 15 current language models as automated approvers, the trusted card raises the attack catch rate from 0.30 to 0.98, at the cost of refusing 16 percent of harmless near misses, mostly due to a placeholder artifact in our stimuli. A second device adds nothing measurable over a trusted on-host confirmation in these experiments, flooding still succeeds 0.45 to 0.60 of the time against a modeled approver, and approval cannot stop effects that policy already allows. Code, data and proofs: https://github.com/Sports-Vision-Inc/agent-step-up

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。

↑