paperSeptember 2026Unreviewed

MPDA: Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models

Xingkai Peng, Jun Jiang, Meng Tong, Shuai Li, Weiming Zhang, Neng H. Yu, Kejiang Chen

IEEE Transactions on Dependable and Secure Computing

Abstract

Text-to-image (T2I) models have been widely applied in generating high-fidelity images across various domains. However, these models may also be abused to produce Not-Safe-for-Work (NSFW) content via jailbreak attacks. Existing jailbreak methods primarily manipulate the textual prompt, leaving potential vulnerabilities in image-based inputs largely unexplored. Moreover, text-based methods face challenges in bypassing the model’s safety filters. In response to these limitations, we propose the Mu

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@article{peng2026mpda,
  title = {{MPDA: Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models}},
  author = {Xingkai Peng and Jun Jiang and Meng Tong and Shuai Li and Weiming Zhang and Neng H. Yu and Kejiang Chen},
  year = {2026},
  month = sep,
  journal = {IEEE Transactions on Dependable and Secure Computing},
  doi = {10.1109/TDSC.2026.3696145},
  url = {https://www.semanticscholar.org/paper/d71b2075655a52c19b88c09dfa9c50250927ade5}
}