Xingxing Wei

7

Papers

40

Total Citations

Papers (7)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

TASAR: Transfer-based Attack on Skeletal Action Recognition

Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning

ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

Towards Transferable Targeted 3D Adversarial Attack in the Physical World