Anduin：一种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
arXiv 论文提出 Anduin，利用链上支付历史为自主 AI 智能体服务商生成抗 Sybil 攻击的信誉评分。研究基于覆盖 16 条区块链、157 天、6600 万笔共 610 万美元的智能体交易数据，将买卖双方支付流建模为二部图，提出 max-flow 及两个放松版评分算法。在 813 名买家上对抗模拟攻击者的评估显示，操纵评分需花费买家总支出的 20%，且比标准协同过滤规则难约 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