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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The internet-of-Vehicle (IoV) can facilitate seamless connectivity betweenconnected vehicles (CV), autonomous vehicles (AV), and other IoV entities.Intrusion Detection Systems (IDSs) for IoV networks can rely on machinelearning (ML) to protect the in-vehicle network from cyber-attacks.Blockchain-based Federated Forests (BFFs) could be used to train ML modelsbased on data from IoV entities while protecting the confidentiality of thedata and reducing the risks of tampering with the data. However, ML modelscreated this way are still vulnerable to evasion, poisoning, and exploratoryattacks using adversarial examples. This paper investigates the impact ofvarious possible adversarial examples on the BFF-IDS. We proposed integrating astatistical detector to detect and extract unknown adversarial samples. Byincluding the unknown detected samples into the dataset of the detector, weaugment the BFF-IDS with an additional model to detect original known attacksand the new adversarial inputs. The statistical adversarial detectorconfidently detected adversarial examples at the sample size of 50 and 100input samples. Furthermore, the augmented BFF-IDS (BFF-IDS(AUG)) successfullymitigates the adversarial examples with more than 96% accuracy. With thisapproach, the model will continue to be augmented in a sandbox whenever anadversarial sample is detected and subsequently adopt the BFF-IDS(AUG) as theactive security model. Consequently, the proposed integration of thestatistical adversarial detector and the subsequent augmentation of the BFF-IDSwith detected adversarial samples provides a sustainable security frameworkagainst adversarial examples and other unknown attacks.

Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems