TY - GEN
T1 - A Lightweight Framework for Emotion Drift and Asymmetry Detection in Explainable Deepfake Analysis
AU - Vishwajeeth, Shruthi
AU - Balachandra,
AU - Dayakshini,
AU - Rao, Santhosha
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - Deepfakes are AI-generated synthetic media created through Generative Adversarial Networks (GANs) that mimic real human expressions with high realism, posing major security and ethical threats. Traditional detectors, primarily CNN and landmark-based, struggle with subtle manipulations and lack interpretability. This paper proposes a lightweight and explainable framework that fuses emotion drift analysis, facial asymmetry detection, and heatmap-based interpretability. By analyzing both behavioral (temporal emotion drift) and structural (asymmetry) cues, this framework improves explainability and robustness.
AB - Deepfakes are AI-generated synthetic media created through Generative Adversarial Networks (GANs) that mimic real human expressions with high realism, posing major security and ethical threats. Traditional detectors, primarily CNN and landmark-based, struggle with subtle manipulations and lack interpretability. This paper proposes a lightweight and explainable framework that fuses emotion drift analysis, facial asymmetry detection, and heatmap-based interpretability. By analyzing both behavioral (temporal emotion drift) and structural (asymmetry) cues, this framework improves explainability and robustness.
UR - https://www.scopus.com/pages/publications/105042353868
UR - https://www.scopus.com/pages/publications/105042353868#tab=citedBy
U2 - 10.1109/AIDE69088.2026.11544732
DO - 10.1109/AIDE69088.2026.11544732
M3 - Conference contribution
AN - SCOPUS:105042353868
T3 - 2026 International Conference on Artificial Intelligence and Data Engineering, AIDE 2026 - Proceedings
SP - 234
EP - 238
BT - 2026 International Conference on Artificial Intelligence and Data Engineering, AIDE 2026 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2026 International Conference on Artificial Intelligence and Data Engineering, AIDE 2026
Y2 - 5 February 2026 through 7 February 2026
ER -