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

Existing side-channel analysis techniques require a leakage model, in theform of a prior knowledge or a set of training data, to establish arelationship between the secret data and the measurements. We introduceside-channel analysis with reinforcement learning (SCARL) capable of extractingdata-dependent features of the measurements in an unsupervised learningapproach without requiring a prior knowledge on the leakage model. SCARLconsists of an auto-encoder to encode the information of power measurementsinto an internal representation, and a reinforcement learning algorithm toextract information about the secret data. We employ a reinforcement learningalgorithm with actor-critic networks, to identify the proper leakage model thatresults in maximum inter-cluster separation of the auto-encoder representation.SCARL assumes that the lower order components of a generic non-linear leakagemodel have larger contribution to the leakage of sensitive data. On alightweight implementation of the Ascon authenticated cipher on the Artix-7FPGA, SCARL is able to recover the secret key using 24K power traces during thekey insertion, or Initialization Stage, of the cipher. We also demonstrate thatclassical techniques such as DPA and CPA fail to identify the correct key usingtraditional linear leakage models and more than 40K power traces.

SCARL: Side-Channel Analysis with Reinforcement Learning on the Ascon Authenticated Cipher