Crossmark

Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing

Crossref DOI link: https://doi.org/10.1007/s11633-025-1602-0

Published Online: 2026-06-17

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Wang, Zehao https://orcid.org/0000-0003-4267-5359
Wang, Lanjun https://orcid.org/0000-0002-7696-5330
License Information

Text and Data Mining valid from 2026-06-17

Version of Record valid from 2026-06-17
More Information

Article History

Received: 28 June 2025

Accepted: 22 September 2025

First Online: 17 June 2026

Declarations of conflict of interest

: The authors declared that they have no conflicts of interest to this work.