VATC：面向 Agentic AI 流量的可验证 QoS 机制，从仿真到真实内核对抗测试
Verifiable Agentic Traffic Class: A Policed Quality-of-Service Mechanism for Agentic AI Traffic, Evaluated from Simulation to Real-Kernel Adversarial Testing
AI 导读
一篇 arXiv 论文提出 Verifiable Agentic Traffic Class（VATC），用保留的 DSCP 标记、路由器侧分类器和限速优先队列来识别并保护 AI 智能体流量。
正文 · 原文
Abstract:Software agents built on large language models generate traffic unlike human web traffic, yet routers have no class for it and cannot verify a sender's claim to be an agent. This paper proposes the Verifiable Agentic Traffic Class (VATC), which combines a reserved Differentiated Services Code Point (DSCP) value declaring agent traffic, a router-side classifier that demotes flows contradicting the declaration to a class served after best-effort traffic, and a rate-limited priority queue. VATC was compared with static Differentiated Services (DiffServ), a dedicated class that trusts the marking, and fq_codel, a per-flow fair-queuing scheduler, in two simulators and on a real Linux kernel. VATC matched DiffServ under steady load. In a constructed burst it cut mean agent queuing delay by 98% relative to DiffServ in simulation (assuming an immediate verdict), at a 12% increase in human delay; most of the gain came from the separate class. Under a spoofed flood in the kernel, the rate limit held human latency 11 times below DiffServ's. Without verification, DiffServ and a tightly configured fq_codel gave legitimate agents lower latency than VATC; a live four-feature classifier then demoted all 20 bulk-shaped spoofers and gave agents 0.30 ms, but missed six spoofers that copied the agent pattern. With emulated network delay, a timing feature of the classifier stopped separating agent from human flows. In real agent harnesses on a congested link, router queueing took 13% to 63% of task time, depending on harness and assumed model latency. The traffic was synthetic or sandbox-scale.
| Comments: | 20 pages, 3 figures, 15 tables; submitted to IEEE Access; code and data at doi:https://doi.org/10.5281/zenodo.23865136 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2611.14211 [cs.LG] |
| (or arXiv:2611.14211v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14211 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Naveen Babu Narayanan Nair [view email]
[v1]
Tue, 10 Nov 2026 15:33:22 UTC (2,469 KB)
来源：arXiv cs.AI · arxiv.org