Search

The accurate identification of internet traffic is crucial for network management. However, the use of encryption techniques and constant changes in network protocols make it difficult to extract useful features for traffic classification. Additionally, there may be limited data availability and a lack of diversity within the dataset, which poses further challenges. To address these issues, our research proposes a novel solution that uses an innovative data augmentation technique. This approach leverages the capabilities of LSTM networks to create synthetic data points that closely resemble real traffic data. By doing so, we can significantly enrich the dataset used for training and improve classification efficiency. We conducted thorough experiments to validate our approach and found that combining LSTM-generated data with actual traffic data leads to notable improvements in classification efficiency. We demonstrated the effectiveness of our methodology using academic and commercial datasets. Our classifier, trained on the generated data, showed a performance boost of 6%. Moreover, when classifying with only half of the time, thus utilizing half of the signal, our approach achieved a notable 4% improvement compared to the original classifier. The inclusion of augmented samples within the training set led to a noticeable improvement in both accuracy and F1-score. These findings compellingly demonstrate our data augmentation strategy's practical utility and efficiency in earlier prediction with improved performance for encrypted traffic classification systems. • Enhanced Traffic Analysis via LSTM Augmentation. • Efficiency Boost: Earlier Traffic Classification. • Improved Classifier Performance with Generated Data. • Diverse Data Synthesis for Improved Classification. [ABSTRACT FROM AUTHOR]

Industrial Internet-of-Things systems suffer from a vast and vulnerable attack surface, raising widespread concerns about shielding IIoT devices from malicious attacks and reducing cyber risks. Device identification is the prerequisite to safeguard IIoT systems. We leverage the observation that IIoT network protocol implementations vary due to different hardware architectures/configurations and design tasks of IIoT devices, which cause the difference in their network traffic payloads. Specifically, we develop a novel neural network to learn the semantic/syntax features among multiple IIoT packets. The neural network has multiple branches, each of which consists of convolution layers, attention modules, and highway units for learning the classification model of IIoT devices. To validate the precision and recall of our neural network in IIoT devices fingerprinting, we have implemented a prototype of the proposed IIoT device identification system. Our results show that our approach achieves 95.8% precision and 95.4% recall, significantly outperforming other classification models. • We propose a novel IIoT fingerprinting approach based on neural network. • We conduct experiments to validate the effectiveness of it. • The results show that our approach can achieve 95.8% precision. • We demonstrate the usefulness of fingerprinting in application. • Our approach is useful in shielding industrial systems. [ABSTRACT FROM AUTHOR]