Skip to content
Hot storiesContinuously updated

LLMjacking盗刷AI密钥攻击与云平台防御指南

1 reports1 reporting sourcesUpdated 23 hours ago

Start here

AI overview

黑客正利用窃取的云凭证与 AI 密钥发起“LLMjacking”攻击，往往在受害者账单上产生数十万至上百万美元的巨额模型费用。针对这一威胁，相关技术防护指南梳理了 AWS、Google Cloud 与 Azure 等主流云平台的应对策略。指南明确指出，常规的预算告警与开销上限机制均存在计费延迟，无法即时止损，而配置每分钟 Token 配额（TPM）是目前唯一能在数分钟内硬性阻断超额调用的有效防线。

AI-generated from reports · Updated 23 hours ago

Latest developmentsNov 4 00:00
针对多主流云平台的防护指南发布，指出TPM配额是快速阻断盗刷的关键防线。

Report timeline

Follow the reports to see different sides of the story.

Nov 4
  1. Hacker News · AISelected
    LLMjacking Defense Guide: Restricting Stolen AI Key Abuse Across AWS, Google Cloud, and Azure

    Addressing LLMjacking attacks where hackers exploit stolen cloud credentials and AI keys to rack up hundreds of thousands to millions of dollars in model usage fees on victims' bills, this article provides a defensive configuration guide across major cloud platforms. Due to billing latency in budget alerts and spending caps, tokens-per-minute (TPM) quotas serve as the only line of defense capable of hard-blocking excessive calls within minutes.

Story heat trend

Current heat 5·Comparable peak 10（Nov 4 01:00）·Comparable change, last 24 hours–

02.557.510Nov4Nov4Nov4Nov4

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.