AAAI 2026technical0 citations
The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans?
Yuan Xun, Xiaojun Jia, Xinwei Liu, Simeng Qin, Hua Zhang
Abstract
Multimodal large reasoning models (MLRMs) have advanced visual-textual integration, enabling sophisticated human-AI interaction. While prior work has exposed MLRMs to visual jailbreaks, it remains underexplored how their reasoning capabilities reshape the security landscape under adversarial inputs. To fill this gap, we conduct a systematic security assessment of MLRMs and uncover a security-reasoning paradox: although deeper reasoning boosts cross‑modal risk recognition, it also creates cognitive blind spots that adversaries can exploit. We observe that MLRMs oriented toward human-centric service are highly susceptible to users
BibTeX
@inproceedings{aaai2026_theemotionalbaby,
title = {The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans?},
author = {Yuan Xun and Xiaojun Jia and Xinwei Liu and Simeng Qin and Hua Zhang},
booktitle = {AAAI 2026},
year = {2026}
}