Score: 1

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning

Published: January 20, 2026 | arXiv ID: 2601.14127v1

By: Renmiao Chen , Yida Lu , Shiyao Cui and more

Potential Business Impact:

Makes AI safer with many pictures.

Business Areas:
Image Recognition Data and Analytics, Software

As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We study this problem by introducing MIR-SafetyBench, the first benchmark focused on multi-image reasoning safety, which consists of 2,676 instances across a taxonomy of 9 multi-image relations. Our extensive evaluations on 19 MLLMs reveal a troubling trend: models with more advanced multi-image reasoning can be more vulnerable on MIR-SafetyBench. Beyond attack success rates, we find that many responses labeled as safe are superficial, often driven by misunderstanding or evasive, non-committal replies. We further observe that unsafe generations exhibit lower attention entropy than safe ones on average. This internal signature suggests a possible risk that models may over-focus on task solving while neglecting safety constraints. Our code and data are available at https://github.com/thu-coai/MIR-SafetyBench.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
15 pages

Category
Computer Science:
CV and Pattern Recognition