arXiv cs.AI· Reza Ramji, Preston Vander Vos, Ziming Zeng, Duc V. Le·· 11 小时前AI 评分31
Anduin：抗女巫攻击的智能体市场声誉系统
Anduin: A sybil-resistant agentic marketplace reputation system
AI 导读
Anduin 提出一套基于链上支付历史的抗女巫攻击声誉系统，用 157 天、16 条区块链上 6600 万笔智能体交易（总额 610 万美元）构建买家与服务商的二部图，并给出 max-flow 等三种评级算法。在 813 名买家与模拟攻击者的测试中，操纵评级需付出这些买家总支出 20% 的代价，难度约为标准协同过滤相似度规则的 23 倍。
正文 · 原文
Abstract:As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge. Existing reputation systems depend on scarce resources like human curation, identity credentials, or voluntary reviews, while naive volume rankings are vulnerable to Sybil attacks.
We evaluate whether existing onchain payment histories can yield provider ratings that are resilient against Sybil attacks. Using a 157-day dataset comprising 66M agentic transactions worth $6.1M across 16 blockchains, we model payment flows as a bipartite graph between buyers and providers. A provider's rating is derived from graph paths linked to a buyer's existing trusted network. We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance.
Evaluating these algorithms against simulated adversaries across 813 buyers, we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.05586 [cs.AI] |
| (or arXiv:2611.05586v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05586 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Duc Le [view email]
[v1]
Tue, 3 Nov 2026 20:17:03 UTC (29 KB)
来源：arXiv cs.AI · arxiv.org