With the speedy advancement of encryption technology and exponential increase in applications, network traffic classification has become an increasingly important research topic. Existing methods for classifying encrypted have certain limitations. For example, traditional approaches such as machine learning rely heavily on feature engineering, deep are susceptible to amount distribution labeled...

The lack of publicly available up-to-date datasets contributes to the difficulty in evaluating intrusion detection systems. This paper introduces HIKARI-2021, a dataset that contains encrypted synthetic attacks and benign traffic. conforms two requirements: content requirements, which focus on produced dataset, process how is built. We compile these requirements enable future developments we ma...

In recent years, privacy awareness is concerned due to many Internet services have chosen use encrypted agreements. order improve the quality of service (QoS), network traffic behaviors are classified based on machine learning discussed in this paper. However, traditional classification methods, such as IP/ASN (Autonomous System Number) analysis, Port-based and deep packet inspection, etc., can...

Network traffic classification has great significance for network security, management and other fields. However, in recent years, the use of VPN TLS encryption had presented with new challenges. Due to performances deep learning image recognition, many solutions have focused on learning-based method achieved positive results. A based is provided this paper, where concept Packet Block proposed,...

We propose a novel traceback approach that marks IP traffic by applying selective marking and reducing load mechanisms. Our technique is adaptive and is exploiting any specific properties that help characterizing an activity in communication traffic. It helps reducing problems such as processing overhead, bandwidth overload, detecting security attacks, and handling encrypted traffic. The select...

This thesis describes how wireless networks can inadvertently leak and broadcast users’ personal information despite the correct use of encryption. Users would likely assume that their activities (for example, the program or app they are using) and personal information (including age, religion, sexuality and gender) would remain confidential when using an encrypted network. However, we demonstr...

Enterprise networks have a complexity that sometimes rival the one of the larger Internet. Still, enterprise traffic has received little attention so far from the research community. Most studies rely on port numbers to identify applications. In this work, we introduce a method to build statistical classifiers to detect specific intranet applications. We exemplify the approach with traces colle...

This paper reports the results of a survey of 1,976 individuals regarding their opinions on TLS inspection, a controversial technique that can be used for both benevolent and malicious purposes. Responses indicate that participants hold nuanced opinions on security and privacy trade-offs, with most recognizing legitimate uses for the practice, but also concerned about threats from hackers or go...

In this paper we introduce a trace-based tunnel that is resistant to traffic analysis in the sense that it provides deniability to users that a specific web page was fetched given that a packet trace is observed on the tunnel. We present a scheduler design for managing the transmission of traces to satisfy user traffic demand while maintaining reasonably low delay and throughput overhead due to...