Preprint
Aug 2026
ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
It is revealed that contexts with stronger semantic-shift capabilities are more likely to guide models toward recovering harmful meanings and achieving successful jailbreaks, and a black-box context-aware semantic-shift jailbreak framework with Iterative Context Optimization is proposed.
Hujian Zhu, Yi-Hao Huang, Felix Juefei-Xu et al.
· 0 citations