From Black Boxes to Glass Boxes: Explainable AI for Trustworthy Deepfake Forensics

As deepfake technology matures, its risks in spreading false information and threatening personal and societal security are escalating. Despite significant accuracy improvements in existing detection models, their inherent opacity limits their practical application in high-risk areas such as forensi...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Hanwei Qian, Lingling Xia, Ruihao Ge, Yiming Fan, Qun Wang, Zhengjun Jing
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2025-09-01
Edice:	Cryptography
Témata:	Deepfake detection explainable AI forensic analysis model interpretability multimodal explanation
On-line přístup:	https://www.mdpi.com/2410-387X/9/4/61
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!