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

Industrial Internet of Things (I-IoT) is a collaboration of devices, sensors,and networking equipment to monitor and collect data from industrialoperations. Machine learning (ML) methods use this data to make high-leveldecisions with minimal human intervention. Data-driven predictive maintenance(PDM) is a crucial ML-based I-IoT application to find an optimal maintenanceschedule for industrial assets. The performance of these ML methods canseriously be threatened by adversarial attacks where an adversary craftsperturbed data and sends it to the ML model to deteriorate its predictionperformance. The models should be able to stay robust against these attackswhere robustness is measured by how much perturbation in input data affectsmodel performance. Hence, there is a need for effective defense mechanisms thatcan protect these models against adversarial attacks. In this work, we proposea double defense mechanism to detect and mitigate adversarial attacks in I-IoTenvironments. We first detect if there is an adversarial attack on a givensample using novelty detection algorithms. Then, based on the outcome of ouralgorithm, marking an instance as attack or normal, we select adversarialretraining or standard training to provide a secondary defense layer. If thereis an attack, adversarial retraining provides a more robust model, while weapply standard training for regular samples. Since we may not know if an attackwill take place, our adaptive mechanism allows us to consider irregular changesin data. The results show that our double defense strategy is highly efficientwhere we can improve model robustness by up to 64.6% and 52% compared tostandard and adversarial retraining, respectively.

DODEM: DOuble DEfense Mechanism Against Adversarial Attacks Towards Secure Industrial Internet of Things Analytics