Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918390337110016 |
|---|---|
| author | Tian, Chong Wang, Yu Yang, Chenxu Guan, Junyi Lin, Zheng Liu, Yuhan Chen, Xiuying Ho, Qirong |
| author_facet | Tian, Chong Wang, Yu Yang, Chenxu Guan, Junyi Lin, Zheng Liu, Yuhan Chen, Xiuying Ho, Qirong |
| contents | Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationships are subtly inconsistent, like mismatched visuals and captions. On two benchmark datasets, FakeSV (Chinese) and FakeTT (English), we observe a clear asymmetry: real videos exhibit high text-visual but moderate text-audio consistency, while fake videos show the opposite pattern. Moreover, a single global consistency score forms an interpretable axis along which fake probability and prediction errors vary smoothly. Motivated by these observations, we present MAGIC3 (Modal-Adversarial Gated Interaction and Consistency-Centric Classifier), a detector that explicitly models and exposes cross-tri-modal consistency signals at multiple granularities. MAGIC3 combines explicit pairwise and global consistency modeling with token- and frame-level consistency signals derived from cross-modal attention, incorporates multi-style LLM rewrites to obtain style-robust text representations, and employs an uncertainty-aware classifier for selective VLM routing. Using pre-extracted features, MAGIC3 consistently outperforms the strongest non-VLM baselines on FakeSV and FakeTT. While matching VLM-level accuracy, the two-stage system achieves 18-27x higher throughput and 93% VRAM savings, offering a strong cost-performance tradeoff. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14992 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos Tian, Chong Wang, Yu Yang, Chenxu Guan, Junyi Lin, Zheng Liu, Yuhan Chen, Xiuying Ho, Qirong Artificial Intelligence Multimedia Short-form video platforms are major channels for news but also fertile ground for multimodal misinformation where each modality appears plausible alone yet cross-modal relationships are subtly inconsistent, like mismatched visuals and captions. On two benchmark datasets, FakeSV (Chinese) and FakeTT (English), we observe a clear asymmetry: real videos exhibit high text-visual but moderate text-audio consistency, while fake videos show the opposite pattern. Moreover, a single global consistency score forms an interpretable axis along which fake probability and prediction errors vary smoothly. Motivated by these observations, we present MAGIC3 (Modal-Adversarial Gated Interaction and Consistency-Centric Classifier), a detector that explicitly models and exposes cross-tri-modal consistency signals at multiple granularities. MAGIC3 combines explicit pairwise and global consistency modeling with token- and frame-level consistency signals derived from cross-modal attention, incorporates multi-style LLM rewrites to obtain style-robust text representations, and employs an uncertainty-aware classifier for selective VLM routing. Using pre-extracted features, MAGIC3 consistently outperforms the strongest non-VLM baselines on FakeSV and FakeTT. While matching VLM-level accuracy, the two-stage system achieves 18-27x higher throughput and 93% VRAM savings, offering a strong cost-performance tradeoff. |
| title | Exposing Cross-Modal Consistency for Fake News Detection in Short-Form Videos |
| topic | Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2603.14992 |