ctf-ai-ml
仓库创建 2026年2月2日最近提交 2 天前SkillHot 收录 20 天前
▸ 精选理由
收录实战脚本与依赖,便于竞赛快速部署与复现攻防用例。
▸ 风险提示
可能包含用于模型操纵或数据破坏的技术,请在合法场景使用。
这个 Skill 做什么
用于 CTF 的 AI/ML 攻击、模型提取与对抗样本速查。
把 AI/ML 相关的 CTF 攻防技术集合成速查手册,覆盖对抗样本、模型提取、prompt 注入、membership inference、数据投毒、LoRA 利用、LLM 越狱等常见套路。碰到要攻破或分析模型、做 adversarial 测试或解决 AI 题目时就用它。特点是把实战命令、依赖和思路浓缩为一页速查,方便快速复现与调试。
▸ 展开 SKILL.md 英文原文
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.
2.8k
Stars
333
Forks
11
仓库内 Skill
+197
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/ljagiello/ctf-skills/main/ctf-ai-ml/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/ljagiello/ctf-skills/main/ctf-ai-ml/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# CTF AI/ML Quick reference for AI/ML CTF challenges. Each technique has a one-liner here; see supporting files for full details. ## Prerequisites **Python packages (all platforms):** ```bash pip install torch transformers numpy scipy Pillow safetensors scikit-learn ``` **Linux (apt):** ```bash apt install python3-dev ``` **macOS (Homebrew):** ```bash brew install python@3 ``` ## Additional Resources - [model-attacks.md](model-attacks.md) - Model weight perturbation negation, model inversion via gradient descent, neural network encoder collision, LoRA adapter weight merging, model extraction via query API, membership inference attack - [adversarial-ml.md](adversarial-ml.md) - Adversar
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有