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

Since training a deep neural network (DNN) is costly, the well-trained deepmodels can be regarded as valuable intellectual property (IP) assets. The IPprotection associated with deep models has been receiving increasing attentionsin recent years. Passport-based method, which replaces normalization layerswith passport layers, has been one of the few protection solutions that areclaimed to be secure against advanced attacks. In this work, we tackle theissue of evaluating the security of passport-based IP protection methods. Wepropose a novel and effective ambiguity attack against passport-based method,capable of successfully forging multiple valid passports with a small trainingdataset. This is accomplished by inserting a specially designed accessory blockahead of the passport parameters. Using less than 10% of training data, withthe forged passport, the model exhibits almost indistinguishable performancedifference (less than 2%) compared with that of the authorized passport. Inaddition, it is shown that our attack strategy can be readily generalized toattack other IP protection methods based on watermark embedding. Directions forpotential remedy solutions are also given.

Effective Ambiguity Attack Against Passport-based DNN Intellectual Property Protection Schemes through Fully Connected Layer Substitution