読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · LLM劫持攻击重大1 分で読めるDisconfirmAI 編集部

Google warns of 'LLMjacking': Hackers steal AI keys to rack up $100k cloud bills in minutes

Google's Threat Intelligence Group reports that cybercriminals are increasingly hijacking enterprise AI API keys and cloud credentials to run unauthorized workloads, generating massive billing charges rapidly.

2026-11-03 23:25 GMT+8

Cybercriminals are stealing AI API keys and cloud credentials to hijack expensive large language model (LLM) services, according to a new report from Google’s Threat Intelligence Group (GTIG). The practice, termed "LLMjacking," involves attackers using stolen access to run AI workloads, create proxy services, and rack up massive bills for victims.

Unlike cryptojacking, where mining is relatively slow, LLMjacking costs can escalate extremely quickly. GTIG noted that one threat actor, identified as UNC6993, generated additional API keys within victim cloud projects after acquiring initial access, "quickly accumulating over $100,000 in billing charges." Another actor subscribed victim accounts to Pay-As-You-Go agreements and launched high-volume inference streams, bypassing rate limits by continuously creating and deleting short-lived service accounts.

The report highlights an emerging division of labor in this cybercrime ecosystem. While some groups focus on establishing initial access through exposed endpoints or stolen identity tokens, others known as "LLM Mixers" manage downstream monetization infrastructure. These operators act as routing gateways, proxying, aggregating, and reselling unauthorized LLM access to underground subscribers.

Google urges organizations to increase visibility into their LLM platforms, prioritize detection of modifications to LLM accounts, and enforce the principle of least privilege to mitigate these risks.

ソース

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク
techradar.comTechRadar↗
トピック

LLM劫持攻击

【背景】“LLM劫持”(LLMjacking)是指攻击者通过窃取API密钥或利用未防护端点,非法占用企业大语言模型算力以发起网络攻击或转售牟利的行为。

2 ステップ2 件更新日 2026-11-06 13:14

経緯

  1. 2026-10-22赛门铁克发布报告,描述了一种能自主劫持未防护大语言模型并执行长达10万步网络攻击的AI智能体,该智能体使用五层越狱指令绕过安全护栏。the-decoder.com ↗
  2. 2026-11-03谷歌威胁情报组(GTIG)与Mandiant联合发布报告,指出黑客通过窃取AI API密钥和云凭证实施“LLM劫持”,导致企业云账单在数分钟内飙升至六位数,并识别出负责转售非法访问权限的“LLM混合器”。techradar.com ↗

未解決の問題

  • 商业大模型提供商是否会调整API定价策略或引入更严格的速率限制以应对高频自动化攻击?
  • 监管机构如何界定“LLM混合器”运营者的法律责任,以及跨境执法协作的实际效果如何?
  • 现有基于身份验证的云安全工具能否有效区分合法的高并发推理请求与恶意的资源耗尽攻击?

このスレッド内の他の記事

  • Symantec Discovers 'LLMjacking': AI Agent Autonomously Hijacks Unprotected Models for Cyberattacks2026-10-22
トピック全文を読む →
リサーチを続ける →