The Limits of SEMA on Distinguishing Similar Activation Functions of Embedded Deep Neural Networks

The Limits of SEMA on Distinguishing Similar Activation Functions of Embedded Deep Neural Networks

Artificial intelligence (AI) is progressing rapidly, and in this trend, edge AI has been researched intensively. However, much less work has been performed around the security of edge AI. Machine learning models are a mass of intellectual property, and an optimized network is very valuable. Trained...

Täydet tiedot

Bibliografiset tiedot
Päätekijät: Go Takatoi, Takeshi Sugawara, Kazuo Sakiyama, Yuko Hara-Azumi, Yang Li
Aineistotyyppi: Artikkeli
Kieli:English
Julkaistu: MDPI AG 2022-04-01
Sarja:Applied Sciences
Aiheet:
machine learning
deep learning
side-channel
activation function
SEMA
Linkit:https://www.mdpi.com/2076-3417/12/9/4135

Internet

https://www.mdpi.com/2076-3417/12/9/4135

Samankaltaisia teoksia