ml-security

涵盖模型加载、数据/模型投毒、PII 与模型血缘的安全建议。

帮你检查和防护模型相关的安全问题：怎么安全地加载模型（优先 safetensors、避免任意 .pkl），识别模型或数据被投毒、训练数据里泄露的 PII，以及笔记本里藏的密钥。会在拉第三方 checkpoint、做微调或把模型放到生产/Notebook 运行时用上。特点是给出具体可操作的加载与验证办法（如 weights_only、校验溯源/签名），把易被忽视的风险点说清楚。

# ML Model Security

## Rules (for AI agents)

### ALWAYS
- When loading models, use **safetensors** for PyTorch and Hugging Face; use
  `weights_only=True` with `torch.load` on PyTorch 2.4+; never load arbitrary
  `.pkl` / `.pt` files from untrusted sources.
- Verify **provenance / lineage** of any third-party or externally fine-tuned
  model — known author, signed or hashed checkpoint, recorded source — before
  loading it.
- Pin and hash **model + dataset versions** and record them, so a poisoned
  artifact can be traced and rolled back.
- Scrub PII, credentials, and secrets from training / fine-tuning data — at the
  source (ingestion), at storage (encryption + access control), and in an