Preprint
Aug 2026
Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models
Text-Anchored Semantic Perturbation Attack (TA-SPA), a black-box jailbreak framework that optimizes transferable perturbations in a text-anchored semantic space and integrates Text-Anchored Semantic Factorization (TASF), which encourages the separation of cross-modal semantic factors from modality-specific residuals.
Wenyun Li, Gui-Ping Cao, Xiang-Yuan Lan et al.
· 0 citations