E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913913039224832 |
|---|---|
| author | Phan, Van-Hoang Pham, Long-Khanh Vu, Dang Tran, Anh-Duy Dao, Minh-Son |
| author_facet | Phan, Van-Hoang Pham, Long-Khanh Vu, Dang Tran, Anh-Duy Dao, Minh-Son |
| contents | The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessment. By dynamically retrieving and cross-referencing trusted data sources, our approach mitigates vulnerabilities of traditional training-based models, such as adversarial attacks and data poisoning. Additionally, its lightweight design enables seamless edge device integration without extensive on-device processing. Experiments on two fact-checking benchmarks achieve SOTA results, confirming its effectiveness in misinformation detection and its robustness against various attack vectors, highlighting its potential to enhance security in mobile and wireless communication environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs Phan, Van-Hoang Pham, Long-Khanh Vu, Dang Tran, Anh-Duy Dao, Minh-Son Multimedia Cryptography and Security The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessment. By dynamically retrieving and cross-referencing trusted data sources, our approach mitigates vulnerabilities of traditional training-based models, such as adversarial attacks and data poisoning. Additionally, its lightweight design enables seamless edge device integration without extensive on-device processing. Experiments on two fact-checking benchmarks achieve SOTA results, confirming its effectiveness in misinformation detection and its robustness against various attack vectors, highlighting its potential to enhance security in mobile and wireless communication environments. |
| title | E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification via MLLMs |
| topic | Multimedia Cryptography and Security |
| url | https://arxiv.org/abs/2506.20944 |