A5045045561- Network Security and Intrusion Detection
- Electrochemical sensors and biosensors
- Advanced Malware Detection Techniques
- Advanced Steganography and Watermarking Techniques
- Information and Cyber Security
- Chaos-based Image/Signal Encryption
- Electrochemical Analysis and Applications
- Supercapacitor Materials and Fabrication
- Software Testing and Debugging Techniques
- Topic Modeling
- Advanced Decision-Making Techniques
- Conducting polymers and applications
- Adversarial Robustness in Machine Learning
- Cryptography and Data Security
- Analytical Chemistry and Sensors
- Advanced biosensing and bioanalysis techniques
- Data Quality and Management
- Digital Media Forensic Detection
- Natural Language Processing Techniques
- Nanoplatforms for cancer theranostics
- Web Application Security Vulnerabilities
- Extracellular vesicles in disease
- Advanced Nanomaterials in Catalysis
- Anomaly Detection Techniques and Applications
- Advanced Graph Neural Networks
National University of Defense Technology
2018-2025
Anhui University
2021-2025
Hunan Xiangdian Test Research Institute (China)
2024
Northeast Normal University
2015-2021
Beijing Forestry University
2021
PLA Electronic Engineering Institute
2010-2017
Penetration testing is an effective way to test and evaluate cybersecurity by simulating a cyberattack. However, the traditional methods deeply rely on domain expert knowledge, which requires prohibitive labor time costs. Autonomous penetration more efficient intelligent solve this problem. In paper, we model as Markov decision process problem use reinforcement learning technology for autonomous in large scale networks. We propose improved deep Q-network (DQN) named NDSPI-DQN address sparse...
Generally, metal–organic framework (MOF)-derived electrocatalysts are prepared by thermal pyrolysis at high temperatures of around 600–900 °C and in inert atmosphere. Herein we introduce a laser-induced method for preparation MOF-derived Co nanoparticle/nitrogen-doped porous graphene (Co/PNG) room temperature air Through laser scribing method, the organic complex is converted into nitrogen-doped (PNG) meanwhile decomposition linker yields reductive chemical This atmosphere energy local...
Green and sustainable electrochemical conversion storage devices possess the nature to repress a negative effect on sustainability during energy storage. However, of devices' components themselves (e.g., raw material abundance, eco-friendliness, recycling) is often ignored, which may damage environment limit practical applicability. Herein, guided by concept sustainability, strategy reported synthesize very cheap single zinc atoms dispersed nitrogen-doped hierarchically porous carbon...
Large language models’ domain-specific capabilities can be enhanced through specialized datasets, yet constructing comprehensive cybersecurity datasets remains challenging due to the field’s multidisciplinary nature. We present PenQA, a novel instructional dataset for penetration testing that integrates theoretical and practical knowledge. Leveraging authoritative sources like MITRE ATT&CK™ Metasploit, we employ online large models generate approximately 50,000 question–answer pairs.We...
Nowadays the amount of cybersecurity data grows quickly on Internet, however most them are textual unstructured data, which is hard for security analysis to understand in time and not suitable automated systems directly use. The real-time switching information from text sources structured representations can help cyber threat intelligence know situation better. Named Entity Recognition (NER) able convert into data. Recently, a language representation model named Bidirectional Encoder...
Further promoting the application of lithium iron phosphate (LFP) requires both a high-rate performance and high volumetric energy density. Nanosizing increased carbon content can improve rate but may decrease Therefore, it is challenging to achieve density excellent simultaneously for LFP. Here, we propose heterogeneous spray-drying method synthesize low-carbon-content hierarchical large microspheres filled with small composed nanosized primary particles. The material was analyzed using...
Abstract The development of artificial intelligence technology has advanced by leaps and bounds made significant progress in many areas. Many researchers have begun to apply the cyber security domain. Knowledge graphs can describe concepts, entities their relationships objective world a structured way. Applying knowledge graph domain organize, manage, utilize massive amounts information cyberspace better In this paper, common assessment models shortcomings is summarized, research...
Non-flammable electrolyte with superior cathode/anode compatibility is enabled ethoxy (pentafluoro) cyclotriphosphazene additive.