~ / skills / security / data-and-model-poisoning

data-and-model-poisoning

Hunt LLM training-data and model poisoning (OWASP LLM04:2025) — adversarial inputs that bias future model behaviour through fine-tuning, RLHF, or continuous-learning loops.

Industry: security
License: Unverified
Source repo: PurpleAILAB/Decepticon · ★ 4,707
Source file: packages/decepticon/decepticon/skills/standard/analyst/data-and-model-poisoning/SKILL.md

View full SKILL.md on GitHub →

不会安装？看中文图文教程 →