| Authors |
Tehsin, Sara ; Nasir, Inzamam Mashood ; Abdelbaki, Wiem ; Alrowais, Fadwa ; Abualhamayel, Reham ; Yahya, Abdulsamad Ebrahim ; Marzouk, Radwa |
| Abstract [eng] |
The rapid proliferation of multimodal misinformation on social media demands detection frameworks that are not only accurate but also robust to noise, adversarial manipulation, and semantic inconsistency between modalities. Existing multimodal fake news detection approaches often rely on deterministic fusion strategies, which limits their ability to model uncertainty and complex cross-modal dependencies. To address these challenges, we propose Q-ALIGNer, a quantum-inspired multimodal framework that integrates classical feature extraction with quantum state encoding, learnable cross-modal entanglement, and robustness-aware training objectives. The proposed framework adopts quantum formalism as a representational abstraction, enabling probabilistic modeling of multimodal alignment while remaining fully executable on classical hardware. Q-ALIGNer is evaluated on four widely used benchmark datasets—FakeNewsNet, Fakeddit, Weibo, and MediaEval VMU—covering diverse platforms, languages, and content characteristics. Experimental results demonstrate consistent performance improvements over strong text-only, vision-only, multimodal, and quantum-inspired baselines, including BERT, RoBERTa, XLNet, ResNet, EfficientNet, ViT, Multimodal-BERT, ViLBERT, and QEMF. Q-ALIGNer achieves accuracies of 91.2%, 92.9%, 91.7%, and 92.1% on FakeNewsNet, Fakeddit, Weibo, and MediaEval VMU, respectively, with F1-score gains of 3–4 percentage points over QEMF. Robustness evaluation shows a reduced adversarial accuracy gap of 2.6%, compared to 7%–9% for baseline models, while calibration analysis indicates improved reliability with an expected calibration error of 0.031. In addition, computational analysis shows that Q-ALIGNer reduces training time to 19.6 h compared to 48.2 h for QEMF at a comparable parameter scale. These results indicate that quantum-inspired alignment and entanglement can enhance robustness, uncertainty awareness, and efficiency in multimodal fake news detection, positioning Q-ALIGNer as a principled and practical content-centric framework for misinformation analysis. |
