English(EN) ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud

新环境ScamWorld测试AI代理对抗在线欺诈

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-05 05:00

研究人员开发了ScamWorld，一个旨在评估网络代理对在线欺诈易感性的交互式环境。该平台重建了报告的诈骗网站，以便对代理如何处理欺骗性界面和欺诈性计划进行可控且可重复的测试。一项使用六个前沿LLM驱动代理的初步研究显示，欺骗率在11%到35%之间，代理比那些要求凭证或钱包信息的代理更容易继续处理付款请求。 AI

影响这项研究为评估AI代理在对抗复杂的在线欺诈策略方面的安全性与鲁棒性提供了一个新的基准。

排序理由该项目是一篇研究论文，详细介绍了一个用于评估AI代理的新环境。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 25 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，详细介绍了一个用于评估AI代理的新环境。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yutao Wu, Xiao Liu, Ming Wen, Hanxun Huang, Jun Wang, Xingjun Ma · 2026-11-05 05:00

ScamWorld：一个用于评估网络代理对抗在线欺诈的交互式环境

arXiv:2611.04879v2 Announce Type: replace Abstract: Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial content, including prompt injections and deceptive interfaces. Beyond such attacks, …

本文如何被排名

报道来源 [1]

ScamWorld：一个用于评估网络代理对抗在线欺诈的交互式环境

相关实体

相关话题