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

Concept drift is a significant challenge for malware detection, as theperformance of trained machine learning models degrades over time, renderingthem impractical. While prior research in malware concept drift adaptation hasprimarily focused on active learning, which involves selecting representativesamples to update the model, self-training has emerged as a promising approachto mitigate concept drift. Self-training involves retraining the model usingpseudo labels to adapt to shifting data distributions. In this research, wepropose MORPH -- an effective pseudo-label-based concept drift adaptationmethod specifically designed for neural networks. Through extensiveexperimental analysis of Android and Windows malware datasets, we demonstratethe efficacy of our approach in mitigating the impact of concept drift. Ourmethod offers the advantage of reducing annotation efforts when combined withactive learning. Furthermore, our method significantly improves over existingworks in automated concept drift adaptation for malware detection.

MORPH: Towards Automated Concept Drift Adaptation for Malware Detection