PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 2, 2026Digital Threats Research and Practice3 citationsOpen Access

Enhancing Digital Security: A Novel Dual-Paradigm Approach for Robust Deepfake Detection Using Pre and Post Quantum-Trained Neural Networks

View Full Paper
SGShashank GuptaYHYashas HariprasadSIS.S. Iyengar

Key Points

  • To develop a dual paradigm framework for improved deepfake detection utilizing classical and quantum-trained models.
  • Developed an attention-enhanced EfficientNetB4 model for the classical deepfake detection stage.
  • Integrated a Quantum Trained Convolutional Neural Network (QT-CNN) to optimize model complexity and accuracy.
  • Conducted experiments on diverse datasets including South Asian celebrities and mainstream benchmarks like FF++ and DFDC.
  • Employed spatial attention and siamese feature alignment techniques to improve detection sensitivity.
  • Achieved 94.5% accuracy on in-distribution data, indicating strong detection performance.
  • Demonstrated robust generalization across demographic and data shifts.
  • Reduced trainable parameters by nearly 70%, enhancing efficiency for real-world application.

Abstract

The rapid rise of deepfake technology continues to challenge digital security, trust, and misinformation control particularly for celebrities and public figures whose identities are frequently exploited. This paper introduces a novel dual paradigm deepfake detection framework that integrates a classical attention enhanced EfficientNetB4 model with a Quantum Trained Convolutional Neural Network (QT-CNN). The classical stage leverages spatial attention and siamese feature alignment to highlight manipulation sensitive facial regions and improve cross-dataset generalization. Building on this, the QT-CNN employs parameterized quantum circuits and quantum to classical parameter mapping to reduce model complexity while preserving detection accuracy. Comprehensive experiments on a large scale South Asian celebrity dataset, an underrepresented demographic in existing benchmarks alongside FF++ and DFDC, demonstrate that the hybrid approach achieves robust performance, including 94.5% accuracy on in-distribution data and strong generalization under demographic, corruption, and compression shifts. The QT-CNN further reduces trainable parameters by nearly 70%, suggesting a promising pathway for efficient deployment in resource constrained, high volume environments such as social media moderation pipelines. This work contributes a scalable, demographically inclusive, and quantum informed methodology toward securing digital ecosystems in both current and emerging post quantum environments.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Gupta et al. (2026) studied this question.

synapsesocial.com/papers/6980ff26c1c9540dea811ddbhttps://doi.org/10.1145/3794846
Ask AI
Helpful
Bookmark
Share
View Full Paper