A multi-turn red-teaming agent trained on simulated attacker-defender conversations induces vulnerable code at higher rates than prior attack methods across several code LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
A multi-turn red-teaming agent trained on simulated attacker-defender conversations induces vulnerable code at higher rates than prior attack methods across several code LLMs.