LeituraPesquisaRadarFramework de investimento
Entrar / Cadastrar
← Voltar para a leitura
NotíciasTópico · ARTEX AI代理框架Material2 min de leituraEditorial DisconfirmAI

Amazon Honeypot Captures ARTEX AI Agent Logs Revealing Self-Sustaining Key Theft and Failed Deepfake KYC Attempts

Amazon's MadPot honeypot captured operational logs from ARTEX AI agents, revealing a self-sustaining loop where stolen LLM API keys funded further credential hunting and real-time deepfakes failed server-side KYC validation.

2026-11-14 04:26 GMT+8

Amazon Threat Intelligence announced on November 13, 2026, that its globally distributed decoy network, MadPot, captured requests from AI agents running offensive campaigns on the open-source framework ARTEX between October 3 and November 5, 2026. The sensors were configured to mimic popular large language model (LLM) inference APIs, causing the agents to send their own operational history—including system prompts, tool execution records, and knowledge graph states—to the honeypot.

The primary campaign involved the industrial-scale theft of credentials to access AI models. Stolen keys were fed back into the framework's own model gateway, creating a self-sustaining loop where computational resources paid for by victims funded the search for more keys. Targets included LLM gateways like One API, New API, and LiteLLM, as well as application builders such as Dify, Langflow, and RAGFlow. The agents exploited default master keys, uninitialized installs, and known vulnerabilities like CVE-2025-3248 (Langflow) and CVE-2026-28797 (RAGFlow).

A second campaign targeted cryptocurrency exchanges, attempting to bypass Know Your Customer (KYC) identity verification using real-time deepfakes. The agents reverse-engineered liveness detection mechanisms and generated forged video at 11.5 frames per second on a single consumer GPU. However, all recorded deepfake attempts failed server-side validation.

Amazon assessed with moderate confidence that these operations were conducted by disparate Chinese-nexus threat groups, citing simplified Chinese prompts, China time-zone configurations, and targeting rules excluding mainland China. The company emphasized that the techniques relied on known weaknesses rather than novel exploits, urging organizations to rotate exposed secrets, patch public platforms, and review indicators of compromise (IOCs) published in the report.

Entrar / Cadastrar
LeituraPesquisaRadarFramework de investimento

Fontes

  • aws.amazon.comAmazon Web Services↗
  • techno-edge.netテクノエッジ TechnoEdge↗
Tópico

ARTEX AI代理框架

ARTEX是一个开源的AI渗透测试框架,自2026年7月发布以来迅速被威胁行为者武器化。尽管原作者在10月因滥用报告删除了GitHub仓库,但通过社区分支和商业版本(ARTEX PRO),该工具仍在广泛传播。美国联邦调查局(FBI)于11月…

7 etapas2 peçasAtualizado 2026-11-19 08:53

Como chegamos aqui

  1. 2026-07-26开发者“Autumn-27”在GitHub上首次发布ARTEX开源AI渗透测试框架。censys.com ↗
  2. 2026-08-18Censys观察到攻击者控制的ARTEX主机开始暴露开放目录,泄露利用程序二进制文件和配置信息。censys.com ↗
  3. 2026-10-07CrowdStrike发布报告,归因一起针对韩国金融机构的攻击使用了ARTEX,导致约67,000人的个人信息泄露。ic3.gov ↗

O que ainda está indefinido

  • ARTEX PRO商业版本的实际用户规模和具体功能增强细节尚未公开。
  • 随着社区分支的快速迭代,新的变种是否引入了更高级的规避检测技术尚不明确。
  • FBI和微软提到的“中国背景”威胁组织的具体身份及其与政府机构的直接联系仍需进一步证据支持。

Também nesta thread

  • FBI warns: AI hacking tool ARTEX breaches networks in under three hours2026-11-17
Ler o tópico completo →
Continuar pesquisando →