English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As a type of valuable intellectual property (IP), deep neural network (DNN)models have been protected by techniques like watermarking. However, suchpassive model protection cannot fully prevent model abuse. In this work, wepropose an active model IP protection scheme, namely NNSplitter, which activelyprotects the model by splitting it into two parts: the obfuscated model thatperforms poorly due to weight obfuscation, and the model secrets consisting ofthe indexes and original values of the obfuscated weights, which can only beaccessed by authorized users with the support of the trusted executionenvironment. Experimental results demonstrate the effectiveness of NNSplitter,e.g., by only modifying 275 out of over 11 million (i.e., 0.002%) weights, theaccuracy of the obfuscated ResNet-18 model on CIFAR-10 can drop to 10%.Moreover, NNSplitter is stealthy and resilient against norm clipping andfine-tuning attacks, making it an appealing solution for DNN model protection.The code is available at: https://github.com/Tongzhou0101/NNSplitter.

NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation