The sharp increase in encrypted traffic brings a huge challenge to traditional traffic
classification methods. Combining deep learning with time series analysis techniques is a …

Network intrusion detection systems (IDS) are often considered effective to thwart cyber
attacks. Currently, state-of-the-art (SOTA) IDSs are mainly based on machine learning (ML) …

The IPv6 extension header mechanism, a new feature of the IPv6 protocol, enhances
flexibility and scalability but introduces numerous security threats like firewall evasion and …

The focus on privacy protection has brought much-encrypted network traffic. However,
attackers always abuse traffic encryption to conceal malicious behaviors. Although …

针对现有人工神经网络方法在网络加密流量分类应用中结构复杂且计算量大的问题,
首次提出了一种基于特征融合的轻量级网络模型Inception-CNN, 用于端到端加密流量的分类 …

摘要加密流量数据包之间具有明显的时序特征, 现有方法很难提取出流量数据中隐含的时序特征
, 未能将时序特征与空间特征有效地融合, 公开数据集大都存在类间样本不平衡的问题 …

The exponential increase in encrypted traffic presents significant challenges to conventional
traffic classification methodologies. The integration of deep learning and time series analysis …

In the field of mobile application traffic analysis, existing methods for accurately identifying
encrypted traffic often encounter challenges due to the widespread adoption of encryption …

Internet of Things (IoT) devices generate a massive quantity of network traffic every moment,
which undoubtedly poses an urgent demand for an accurate and efficient network protocol …

요 약근래 등장한 심층신경망 기술의 발달로 인해 인공지능/기계학습 기술은 다양한
산업분야에서 지능화를 통한 비즈니스 혁신을 이끄는 핵심기술로 주목받고 있다. 이에 따라 …