人工智能黑客
AI 安全资源

攻击指南中心

关于 AI 和 LLM 安全攻击技术的综合指南。每个指南都包含现实世界的示例、严重性评级和防御对策。

初学者之路

人工智能安全新手?请遵循以下推荐的阅读顺序:

  1. RAG 特定安全测试框架 — 了解 LLM 安全风险的情况。
  2. 提示注入指南 — 通过实践示例掌握#1 LLM 漏洞。
  3. RAG 安全 — 了解 RAG 系统如何被毒害和操纵。
  4. MCP 安全 — 探索模型上下文协议漏洞。
  5. 红队方法论 — 将结构化对抗性测试应用于人工智能系统。

按类别划分的攻击技术

提示注入

CRITICAL

通过制作恶意输入来操纵 LLM 行为。包括直接注入、通过外部数据源间接注入、多轮越狱等。

阅读指南 →

数据泄露

CRITICAL

从 LLM API 和模型端点提取敏感训练数据、系统提示或内部配置。

阅读指南 →

模型提取

HIGH

通过精心设计的查询和输出分析来窃取模型权重、架构或功能。

阅读指南 →

供应链攻击

HIGH

毒害模型注册表、破坏训练管道或将恶意代码注入人工智能框架和依赖项。

阅读指南 →

拉格中毒

HIGH

将恶意文档注入向量数据库、操纵嵌入或毒害检索结果以改变 LLM 输出。

阅读指南 →

代理目标劫持

MEDIUM

通过操纵上下文或工具输出,将自主人工智能代理从预期目标重定向到恶意目标。

阅读指南 →

函数调用注入

MEDIUM

通过操纵工具描述和对话上下文,强制法学硕士调用非预期的函数或 API。

阅读指南 →

对抗性例子

LOW

针对视觉、音频和文本模型,精心设计微妙的输入扰动,导致模型错误分类或产生不正确的输出。

阅读指南 →

最新补充

准备好测试您的技能了吗?

通过我们的实践测试指南和工具推荐应用您所学到的知识。

浏览工具 → 获取清单 → 查看方法论 →
AH
AI Hacking Team

The AI Hacking team researches and documents AI/LLM security vulnerabilities, red teaming techniques, and defensive strategies. Our guides are based on real-world pentesting experience and continuous monitoring of the AI security landscape.

Frequently Asked Questions

What are the most common techniques for attacking AI systems?
The most common AI attack techniques include prompt injection (direct and indirect), model extraction via API queries, data exfiltration through LLM outputs, adversarial example generation, supply chain attacks via trojaned models, and denial-of-service against inference endpoints.
How do prompt injection attacks work in practice?
Prompt injection works by crafting input that overrides the AI's system instructions. Attackers use techniques like: role-playing (convincing the AI it is in debug mode), delimiter injection (breaking out of input boundaries), encoding bypasses (Base64, Unicode), and indirect injection through documents, web pages, or MCP tool outputs the AI processes.
What is model extraction and how can it be performed?
Model extraction is the process of stealing an AI model's capabilities by sending carefully crafted API queries and analyzing the outputs. Attackers perform extraction via: black-box probing to reconstruct model behavior, side-channel attacks on hardware, and exploiting verbose error messages that leak model architecture details.
How do supply chain attacks target AI/ML systems?
Supply chain attacks target AI/ML systems through: trojaned models on repositories like Hugging Face containing hidden backdoors, typosquatting packages mimicking popular libraries (TensorFlow, PyTorch, transformers), compromised CI/CD pipelines injecting malicious code, and poisoned training data from untrusted sources.

Stay Ahead of AI Security

Get the latest AI/LLM security research, OWASP updates, and new vulnerabilities delivered straight to your inbox.