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

This paper contributes to the study of PUFs vulnerability against modelingattacks by evaluating the security of XOR BR PUFs, XOR TBR PUFs, and obfuscatedarchitectures of XOR BR PUF using a simplified mathematical model and deeplearning (DL) techniques. Obtained results show that DL modeling attacks couldeasily break the security of 4-input XOR BR PUFs and 4-input XOR TBR PUFs withmodeling accuracy $\sim$ 99%. Similar attacks were executed using single-layerneural networks (NN) and support vector machines (SVM) with polynomial kerneland the obtained results showed that single NNs failed to break the PUFsecurity. Furthermore, SVM results confirmed the same modeling accuracyreported in previous research ($\sim$ 50%). For the first time, this researchempirically shows that DL networks can be used as powerful modeling techniquesagainst these complex PUF architectures for which previous conventional machinelearning techniques had failed. Furthermore, a detailed scalability analysis isconducted on the DL networks with respect to PUFs' stage size and complexity.The analysis shows that the number of layers and hidden neurons inside everylayer has a linear relationship with PUFs' stage size, which agrees with thetheoretical findings in deep learning. Consequently, A new obfuscatedarchitecture is introduced as a first step to counter DL modeling attacks andit showed significant resistance against such attacks (16% - 40% lessaccuracy). This research provides an important step towards prioritizing theefforts to introduce new PUF architectures that are more secure andinvulnerable to modeling attacks. Moreover, it triggers future discussions onthe removal of influential bits and the level of obfuscation needed to confirmthat a specific PUF architecture is resistant against powerful DL modelingattacks.

Going Deep: Using deep learning techniques with simplified mathematical models against XOR BR and TBR PUFs (Attacks and Countermeasures)