A5052400360- Network Security and Intrusion Detection
- Internet Traffic Analysis and Secure E-voting
- Software-Defined Networks and 5G
- Advanced Malware Detection Techniques
- Biometric Identification and Security
- Cryptography and Data Security
- Algorithms and Data Compression
- Energy Efficient Wireless Sensor Networks
- Security and Verification in Computing
- Anomaly Detection Techniques and Applications
- Mobile Agent-Based Network Management
- Advanced Steganography and Watermarking Techniques
- Advanced Data Compression Techniques
- Network Packet Processing and Optimization
Tsinghua University
2019-2024
Network Technologies (United States)
2024
Peng Cheng Laboratory
2022
Center for Information Technology
2020
National Engineering Research Center for Information Technology in Agriculture
2019
As the majority of Internet traffic is encrypted by Transport Layer Security (TLS) protocol, recent advances leverage Deep Learning (DL) models to conduct classification. We propose Rosetta enable robust TLS classification for existing DL models. It leverages TCP-aware augmentation mechanisms and self-supervised learning understand implicit TCP semantics, hence extracts features flows. Extensive experiments show that can significantly improve performance on in diverse network environments.
The low-rate TCP attack is essentially a great threat to the Internet. It causes significant throughput degradation of flows by generating periodical pulsing flows. Due its low rate, difficult be detected and throttled. Recently, Software-Defined Networking (SDN) has emerged as promising network paradigm. Several SDN-based defense systems have been proposed deal with various Denial Service (DoS) attacks. However, they fail consider attack. In this paper, we propose SoftGuard, which an that...
Software-Defined Networking (SDN). SDN enables network innovations with a centralized controller controlling the whole through control channel. Because channel delivers all traffic, its security and reliability are of great importance. For first time in literature, we propose CrossPath attack that disrupts by exploiting shared links paths traffic data traffic. In this attack, crafted can implicitly disrupt forwarding links. As does not enter channel, is stealthy cannot be easily perceived...
Software-Defined Networking (SDN) greatly meets the need in industry for programmable, agile, and dynamic networks by deploying diversified SDN applications on a centralized controller.However, application ecosystem inevitably introduces new security threats since compromised or malicious can significantly disrupt network operations.Thus, number of effective enhancement systems have been developed to defend against potential attacks from applications.In this paper, we identify vulnerability...
BGP is the only inter-domain routing protocol that plays an important role on Internet. However, suffers from route leak, which can cause serious security threats. To mitigate effects of accurate and timely leak location great importance. Prior studies leverage AS business relationships to locate in real time. they fail achieve high accuracy. Recent apply machine learning accurately detect statistical features massive messages. Nevertheless, have detection latency cannot further leak. In...
Border Gateway Protocol (BGP) plays a pivotal role as the de facto inter-domain routing protocol on Internet. However, BGP threats continually emerge and undermine Internet reliability. Existing threat detection methods based machine learning require substantial labeled data expert involvement, making them costly labor-intensive. Moreover, they fail to learn rich information from massive unlabeled consistently generated In this paper, we propose FIRE that enables few-shot with large-scale...