PRJA achieves 83.6% average success injecting harmful content into LRM reasoning chains on five QA datasets without altering final answers.
arXiv preprint arXiv:2503.16040 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
PRJA achieves 83.6% average success injecting harmful content into LRM reasoning chains on five QA datasets without altering final answers.