Under the Skin: Backdoor Infection in Multimodal Large Language Models

arXiv:2610.24058v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive performance in generating text conditioned on inputs from different modalities. In this work, we introduce backdoor infection, a cross-modal attack framework targeting MLLMs. Starting from a model already injected with a backdoor in one modality, our attack constructs a corresponding trigger in another modality, called the infected modality.

Read the full article at arXiv cs.CR →