Junwei Liang

ORCID: 0000-0003-1999-0254
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Vehicular Ad Hoc Networks (VANETs)
  • Network Security and Intrusion Detection
  • Blockchain Technology Applications and Security
  • Traffic control and management
  • Autonomous Vehicle Technology and Safety
  • Internet Traffic Analysis and Secure E-voting
  • Opportunistic and Delay-Tolerant Networks
  • Biometric Identification and Security
  • Network Packet Processing and Optimization
  • Human Mobility and Location-Based Analysis
  • Remote Sensing in Agriculture
  • Metaheuristic Optimization Algorithms Research
  • Advanced Steganography and Watermarking Techniques
  • Plant Pathogens and Resistance
  • Face and Expression Recognition
  • Smart Grid Security and Resilience
  • Artificial Immune Systems Applications
  • Plant Disease Resistance and Genetics
  • IoT and Edge/Fog Computing
  • Advanced Authentication Protocols Security
  • Plant Pathogens and Fungal Diseases
  • Remote Sensing and LiDAR Applications
  • Anomaly Detection Techniques and Applications
  • Security in Wireless Sensor Networks
  • Advanced Malware Detection Techniques

Hong Kong University of Science and Technology
2024

University of Hong Kong
2024

Shenzhen Institute of Information Technology
2021-2023

Guizhou University
2023

Nanyang Technological University
2018-2022

Shenzhen University
2016-2019

10.1109/cvprw63382.2024.00575 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2024-06-17

Vehicle ad hoc networks (VANETs) are considered to be the next big thing that will remarkably change our lives, since this kind of technology is able make lives and roads safer. Due very fast move high dynamic in VANETs, it important quickly ascertain reliability information. Although intrusion detection system (IDS) has been proposed as a reliable approach protect VANETs against attacks, its overhead serious, which spends too much time on detection, especially when number vehicles...

10.1109/tits.2019.2905415 article EN IEEE Transactions on Intelligent Transportation Systems 2019-06-10

Due to the nature of high mobility and dynamic network topology, Intrusion Detection Systems (IDSs) in Vehicular Ad-hoc Networks (VANETs) face lots challenges, especially balancing accuracy efficiency detection. Current researches about deployment IDSs VANETs mainly focus on a tradeoff between effectiveness efficiency, but few efforts have been done adaptability changeable networks. Thus, we address two crucial problems: 1) how perceive environmental change perspective an IDS? 2) make IDS...

10.1109/tits.2021.3117028 article EN IEEE Transactions on Intelligent Transportation Systems 2021-10-15

Intrusion Detection System (IDS) is one of the most important approaches in cyber security to protect networks against both inner and outer threats. Apart from traditional networks, IDSs have been implemented various emerging such as mobile Vehicle Ad hoc Networks (VANETs). However, a critical problem that detection capacity gradually decaying with emergence unknown attacks. It necessary constantly retrain more extensive database, but institutes usually lack motivation persistently update...

10.1109/tnsm.2021.3064607 article EN IEEE Transactions on Network and Service Management 2021-03-08

Vehicle Ad Hoc Networks (VANETs) are considered to be a next big thing that will remarkably change our lives, since this kind of technology is able make lives and roads safer. Intrusion Detection Systems (IDS) an important can mitigate both inner outer threats for the vulnerable networks like VANETs. However, it difficult adopt same IDSs have been appropriately used in wired networks, due fast moving highly dynamic nature Thus, article, Efficient Collaborative Framework with Markov-based...

10.1109/tifs.2020.3013211 article EN IEEE Transactions on Information Forensics and Security 2020-07-30

For Intrusion Detection Systems (IDSs) in Vehicular Ad Hoc Networks (VANETs), single-objective optimization algorithm has inherited limitations for the feature selection problem with multiple objectives. Moreover, imbalanced commonly exists various datasets. Thus, this paper, a based on many-objective (FS-MOEA) is proposed IDSs VANETs, which Adaptive Non-dominant Sorting Genetic <xref ref-type="algorithm" rid="alg3" xmlns:mml="http://www.w3.org/1998/Math/MathML"...

10.1109/tits.2020.3011452 article EN IEEE Transactions on Intelligent Transportation Systems 2020-08-03

Intrusion detection systems (IDSs) is crucial for the security of Vehicle Ad Hoc Networks (VANETs), as it can accurately detect both inner and outer attacks. However, redundant features sparse samples fatal attacks in VANETs datasets cause heavy time-consumption imbalanced problems respectively. In this paper, a feature selection algorithm based on many-objective optimization (FS-MOEA) proposed IDSs VANETs, which Non-dominant Sorting Genetic Algorithm-III (NSGA-III) serves evolutionary...

10.1145/3409934.3409953 article EN 2020-07-08

Vehicle Ad Hoc Networks (VANETs) are considered to be a next big thing that will remarkably change our lives, since this kind of technology is able make lives and roads safer. Intrusion Detection Systems (IDS) an important can mitigate both inner outer threats for the vulnerable networks like VANETs. However, it difficult adopt same IDSs have been appropriately used in wired networks, due fast moving highly dynamic nature Thus, paper, Efficient IDS with Markov-based Reputation Scheme...

10.1109/icc42927.2021.9500320 article EN ICC 2022 - IEEE International Conference on Communications 2021-06-01

Recently, Vehicular Ad Hoc Networks (VANETs) have emerged as a promising approach to improve ride comfortability and safety, well increase the competition of highway. Certificate Revocation List (CRL)-based schemes are most widely used recovery mechanism for VANETs eliminate negative effect security privacy attacks. However, providing an efficient low-cost CRL-based scheme certificate revocation is still challenging issue since communication resources must be capable carrying various...

10.1109/wcnc55385.2023.10118685 article EN 2022 IEEE Wireless Communications and Networking Conference (WCNC) 2023-03-01

Intrusion Detection System (IDS) is an effective way to detect both internal and external abnormal behaviors, which has been widely deployed in industrial Cyber-Physical Systems (CPSs). However, due the data island problem caused by imperativeness of confidentiality sensitive information, most existing IDSs are limited be trained evaluated isolated CPSs, resulting cyber systems vulnerable various newly-emerging attacks. In this article, a secure collaborative IDS solution, called PFD-GAN,...

10.1109/globecom54140.2023.10437148 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2023-12-04

Intrusion Detection Systems (IDS) is an important technology for cyber security, as it can mitigate both inner and outer threats in networks. However, a critical problem IDSs that the detection capacity gradually decaying with emergence of unknown attacks. To constantly retrain more extensive database to make adaptive ever-changing network environment, but security institutes usually lack motivation persistently update maintain public. Thus, this paper, blockchain-based (bc-DB) proposed,...

10.1109/globecom42002.2020.9322308 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2020-12-01

Because of the nature high mobility and dynamic network topology, Intrusion Detection Systems (IDSs) in Vehicular Ad-hoc Networks (VANETs) face challenge balancing accuracy efficiency detection. Two crucial problems are remained unsolved existing studies: 1) how to perceive environmental change perspective an IDS? 2) make IDS adaptive different scenarios? In this paper, a self-adaptive scheme is proposed for IDSs VANETs based on Bayesian game theory Deep Q-learning Network (DQN). scheme,...

10.1109/globecom48099.2022.10000649 article EN GLOBECOM 2022 - 2022 IEEE Global Communications Conference 2022-12-04
Coming Soon ...