paperApril 2026Unreviewed

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Kun Wang, Cheng Qian, Miao Yu, Lilan Peng, Liang Lin, Jiaming Zhang, Tianyu Zhang, Yu Cheng, Yang Wang

Abstract

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the feasibility of backdoors in MLLMs via fine-tuning data poisoning to manipulate inference, the underlying mechanisms of backdoor attacks remain opaque, complicating the understanding and mitigation. To bridge this gap, we propose ProjLens, an interpretability framework d

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{wang2026projlens,
  title = {{ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety}},
  author = {Kun Wang and Cheng Qian and Miao Yu and Lilan Peng and Liang Lin and Jiaming Zhang and Tianyu Zhang and Yu Cheng and Yang Wang},
  year = {2026},
  month = apr,
  eprint = {2604.19083},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.19083}
}