CoT-Guard is a 4B model using SFT and RL that achieves 75% G-mean^2 on hidden objective detection under prompt and code manipulation attacks, outperforming several larger models.
Bandit.https://github.com/PyCQA/bandit, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
CoT-Guard: Small Models for Strong Monitoring
CoT-Guard is a 4B model using SFT and RL that achieves 75% G-mean^2 on hidden objective detection under prompt and code manipulation attacks, outperforming several larger models.