Jianxin Wei

Xinjian Luo

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Xinjian Luo (1)Hongyan Chang (1)Yuncheng Wu (1)Xiaofeng Gao (1)

Papers (1)

Jun 17, 2026

Xinjian Luo3w ago·also Augusta University, MBZUAI, McGill

Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks

Intermediate embeddings in distributed MLLM frameworks can leak sensitive image prompts, with new attacks achieving 100% extraction accuracy and revealing serious privacy implications.

Xinjian Luo, Hongyan Chang, Jianxin Wei +5

Multimodal Models Red-Teaming & Adversarial Robustness

Search

Jianxin Wei

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)