ValidCNN: A Large-Scale CNN Predictive Integrity Verification Scheme Based on zk-SNARK

The integrity of cloud-based convolutional neural network (CNN) prediction services can be jeopardized by a malicious cloud server. Although zero-knowledge proof approaches can be used to verify integrity, they are difficult to use for larger CNN models like LeNet-5 and VGG16, due to the large cost...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on dependable and secure computing 2024-11, Vol.21 (6), p.5185-5195
Hauptverfasser:	Fan, Yongkai, Ma, Kaile, Zhang, Linlin, Lei, Xia, Xu, Guangquan, Tan, Gang
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Computational efficiency Computational modeling Convolutional neural networks Integrated circuit modeling Integrity Predictions predictive integrity Predictive models Protocols Training Zero-knowledge proofs zkSNARKs
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!