A5100442307- Advanced Data Storage Technologies
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Caching and Content Delivery
- Mobile Ad Hoc Networks
- Internet Traffic Analysis and Secure E-voting
- Adversarial Robustness in Machine Learning
- Energy Efficient Wireless Sensor Networks
- Cooperative Communication and Network Coding
- Security in Wireless Sensor Networks
- Anomaly Detection Techniques and Applications
- Cellular Automata and Applications
- Cloud Computing and Resource Management
- Topic Modeling
- Wireless Networks and Protocols
- Spam and Phishing Detection
- Distributed systems and fault tolerance
- Advanced Database Systems and Queries
- Software Testing and Debugging Techniques
- Distributed and Parallel Computing Systems
- Network Traffic and Congestion Control
- Full-Duplex Wireless Communications
- Data Management and Algorithms
- Natural Language Processing Techniques
- Peer-to-Peer Network Technologies
Central South University
2016-2025
Institute of Information Engineering
2015-2024
Chinese Academy of Sciences
2007-2024
University of Chinese Academy of Sciences
2018-2024
Shenyang Pharmaceutical University
2023-2024
Chinese University of Hong Kong, Shenzhen
2020
University of Science and Technology Beijing
2016
Xinjiang Uygur Autonomous Region Disease Prevention and Control Center
2013
North China Electric Power University
2013
Beijing Institute of Technology
2007-2008
Identification of essential proteins plays a significant role in understanding minimal requirements for the cellular survival and development. Many computational methods have been proposed predicting by using topological features protein-protein interaction (PPI) networks. However, most these ignored intrinsic biological meaning proteins. Moreover, PPI data contains many false positives negatives. To overcome limitations, recently research groups started to focus on identification...
Through well-designed counterfeit websites, phishing induces online users to visit forged web pages obtain their private sensitive information, e.g., account number and password. Existing antiphishing approaches are mostly based on page-related features, which require crawl content of as well accessing third-party search engines or DNS services. This not only leads low efficiency in detecting but also makes them rely network environment services heavily. In this paper, we propose a fast...
Large Language Models (LLMs) have revolutionized natural language processing tasks with remarkable success. However, their formidable size and computational demands present significant challenges for practical deployment, especially in resource-constrained environments. As these become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate limitations. This paper presents comprehensive survey that navigates landscape techniques tailored...
In environments where sensor networks are used to monitor sensitive objects or valuable assets, attackers may use the method of hop-by-hop backtracking find out protected objects. This paper proposes a new source protocol in WSN, phantom routing with locational angle (PRLA). PRLA, inclination angles introduced and direct random walks, which avoids choosing paths harmful privacy location. Simulation results show that, compared single-path proposed literature, PRLA improves safety period by up...
Multi-component based Log-Structured Merge-tree (LSM-tree) has been becoming one of the mainstream indexes. LSM-tree adopts component-by-component KV item flowing down mechanism to push each from smaller component adjacent larger during compaction procedures until items reach largest component. This process incurs significant write amplification and limits throughput. In this paper, we propose multi-component Skip-tree aggressively non-adjacent components via skipping some then make items'...
Malware detection is an important and challenging issue in the Android ecosystem. Many approaches have been proposed to distinguish malicious applications from benign ones, but few of them can represent behavior patterns help understand their intention. In this paper, we propose LSCDroid, a malware detecting approach that cannot only detect also malware's intention by analyzing its patterns. LSCDroid uses local sensitive application programming interface (API) invocation (LSAI) sequences as...
With the popularity of Android intelligent terminals, malicious applications targeting platform are growing rapidly. Therefore, efficient and accurate detection software becomes particularly important. Dynamic API call sequences widely used in malware because they can reflect behaviours accurately. However, raw dynamic very usually too long to be directly used, most existing works just use a truncated segment sequence or statistical features perform detection, which loses execution order...
Based on the changeability of wireless network circumstance, information packets are prone to lose in process transmission. In broadcasting ,any node multi-nodes request retransmission .This paper presents a novel approach based coding (NCWBR), whose key idea is combine different lost with achieve retransmission. Theoretical analysis reveals that our can ensure solvability received nodes, and have better performance. Simulation results indicate compared existing approach, this effectively...
Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. In backdoor attacks, attackers try to plant hidden backdoors into DNN models, either training or inference stage, mislead output of model when input contains some specified triggers without affecting prediction normal inputs not containing triggers. As a rapidly developing topic, numerous works on designing various and techniques defend against such been proposed recent However,...
In many applications, transaction data arrive in the form of high speed streams. These contain a lot information about customers that needs to be carefully managed protect customerspsila privacy. this paper, we consider problem preserving customerpsilas privacy on sliding window This is challenging because updated frequently and rapidly. We propose novel approach, SWAF (sliding anonymization framework), solve by continuously facilitating k-anonymity window. Three advantages make practical:...
Evidence shows that biological systems are composed of separable functional modules. Identifying protein complexes is essential for understanding the principles cellular functions. Many methods have been proposed to mine from protein-protein interaction networks. However, performances these algorithms not good enough since interactions detected experiments complete and noise. This paper presents an analysis topological properties show although proteins same complex more highly connected than...
Deep learning techniques such as convolutional neural networks (CNNs) have been used in a wide range of fields due to their superior performance, e.g., image classification, autonomous driving and natural language processing. However, recent progress shows that deep models are vulnerable adversarial samples, which crafted by adding small perturbations on normal samples imperceptible human beings but can mislead the output incorrect results. Many attack proposed many detection methods...
Gesture recognition based on radio frequency identification (RFID) has attracted much research attention in recent years. Most existing RFID-based gesture approaches use signal profile matching to distinguish different gestures, which incur large latency and fail support real-time applications. In this paper, we design implement ReActor, a accurate system that recognizes user's gestures with low high accuracy even when the gestures'speed varies. ReActor combines time-domain statistical...
Performing accurate sensing in diverse environments is a challenging issue wireless technologies. Existing solutions usually require collecting large number of samples to train classifier for every environment, or further assume similar sample distribution between different such that model trained one environment can be transferred another. In this paper, we propose RF-Siamese, an RFID-based gesture approach achieves comparable accuracy existing but requires only few each eivironment....
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data. Due to time consumption, storage burden and privacy of old data, it is inadvisable train the model scratch with both data when emerge after trained. In this paper, we propose a novel incremental detector Faster R-CNN continuously learn using It triple where an residual as assistants for helping previous learned knowledge. To better...