Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

arXiv:2608.27531 · cs.CR, cs.CV · Submitted 2026-08-27 · Read on arXiv

cs.CR, cs.CV

Submitted: 2026-08-27

Updated: 2026-09-03

Comments: Accepted by EMNLP 2026 Main Conference

Code: https://github.com/Alibaba-VELLDEPTH/MetaJailbreak-VLM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Meta-Adaptive Multimodal Jailbreaking — 1× in this paper

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs