~ / skills / productivity / aatmf-t06-training-poisoning

aatmf-t06-training-poisoning

AATMF T6 — Training & Feedback Poisoning. Data poisoning, RLHF reward hacks, fine-tune-time exfil, embedding poisoning.

Industry
productivity
License
Unverified
Source repo
PurpleAILAB/Decepticon · ★ 4,707
Source file
packages/decepticon/decepticon/skills/plugins/llm-redteam/t06-training-poisoning/SKILL.md
View full SKILL.md on GitHub →

不会安装?看中文图文教程 →