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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Machine learning (ML) is promising in accurately detecting malicious flows inencrypted network traffic; however, it is challenging to collect a trainingdataset that contains a sufficient amount of encrypted malicious data withcorrect labels. When ML models are trained with low-quality training data, theysuffer degraded performance. In this paper, we aim at addressing a real-worldlow-quality training dataset problem, namely, detecting encrypted malicioustraffic generated by continuously evolving malware. We develop RAPIER thatfully utilizes different distributions of normal and malicious traffic data inthe feature space, where normal data is tightly distributed in a certain areaand the malicious data is scattered over the entire feature space to augmenttraining data for model training. RAPIER includes two pre-processing modules toconvert traffic into feature vectors and correct label noises. We evaluate oursystem on two public datasets and one combined dataset. With 1000 samples and45% noises from each dataset, our system achieves the F1 scores of 0.770,0.776, and 0.855, respectively, achieving average improvements of 352.6%,284.3%, and 214.9% over the existing methods, respectively. Furthermore, Weevaluate RAPIER with a real-world dataset obtained from a security enterprise.RAPIER effectively achieves encrypted malicious traffic detection with the bestF1 score of 0.773 and improves the F1 score of existing methods by an averageof 272.5%.

Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic