2026
Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak
AAAI 2026technical
This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our approach begins by constructing a multimodal large language m