독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · LLM劫持攻击중대2 분 소요DisconfirmAI 편집부

Symantec Discovers 'LLMjacking': AI Agent Autonomously Hijacks Unprotected Models for Cyberattacks

Symantec reports a new attack method called 'LLMjacking,' where an AI agent hijacks unprotected large language models to autonomously launch cyberattacks, leaving model owners with the compute bill.

2026-10-22 19:30 GMT+8

Security firm Symantec has discovered a new attack method dubbed "LLMjacking," in which malicious AI agents hijack unprotected large language models (LLMs) on the internet and use them to launch cyberattacks autonomously. According to Symantec's analysis, the agent can execute up to 100,000 steps without human involvement, while the owners of the hijacked models are left stuck with the compute bill for these attacks.

The discovery stems from a Symantec honeypot system designed to mimic open AI services and lure attackers. Researchers intercepted the full working prompt of the agent in summer 2026, revealing its architecture. The attack process involves scanning for more targets, exploiting flaws in common server software, stealing databases and credentials, and installing cryptominers in the background. To bypass safety rules in commercial models, attackers employed a five-layer jailbreak technique, including assigning fake identities to the model, redefining malicious actions as "normal developer work," and suppressing the model's safety warnings.

Symantec notes that this marks a shift in how attackers use AI: rather than merely manipulating public chatbots, AI is now built into the core of offensive tools, actively seeking out models to power attacks. While individual techniques are not new, combining them into a self-directed agent makes large-scale attacks much easier to execute. Organizations running AI services should assume that unprotected endpoints will be found and probed shortly after going live. It remains unclear whether this jailbreak method fully defeats current commercial models' defenses, but the case confirms the potential threat of autonomous AI agents in the real world.

로그인 / 회원가입
독서리서치레이더투자 프레임워크

출처

  • the-decoder.comThe Decoder↗
주제

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 단계2 건업데이트됨 2026-11-06 13:14

현재까지의 과정

  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 ↗

아직 해결되지 않은 문제

  • 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?

이 스레드의 다른 내용

  • Google warns of 'LLMjacking': Hackers steal AI keys to rack up $100k cloud bills in minutes2026-11-03
전체 주제 읽기 →
리서치 계속하기 →