A5100663395- Software Engineering Research
- Advanced Malware Detection Techniques
- Natural Language Processing Techniques
- Cultural Insights and Digital Impacts
- Image and Video Quality Assessment
- Topic Modeling
- Cryptography and Data Security
- China's Socioeconomic Reforms and Governance
- Advanced Wireless Network Optimization
- Video Coding and Compression Technologies
- Cloud Data Security Solutions
- Service-Oriented Architecture and Web Services
- Security and Verification in Computing
- Chaos-based Image/Signal Encryption
- Spam and Phishing Detection
- Web Data Mining and Analysis
- Network Security and Intrusion Detection
- Cryptographic Implementations and Security
- Wastewater Treatment and Nitrogen Removal
- Cooperative Communication and Network Coding
- Vehicular Ad Hoc Networks (VANETs)
- Cognitive Computing and Networks
- Cognitive Radio Networks and Spectrum Sensing
- Advanced Database Systems and Queries
- Rough Sets and Fuzzy Logic
Nanjing Hydraulic Research Institute
2025
Nanjing University
2022-2025
Nankai University
2022-2024
Le Mans Université
2023
Centre de Recherche en Éducation de Nantes
2023
Centre Nantais de Sociologie
2023
University of Michigan
2020-2022
Data Assurance and Communication Security
2022
National Taiwan University of Science and Technology
2020
Shanghai Jiao Tong University
2019
To support software developers in understanding and maintaining programs, various automatic code summarization techniques have been proposed to generate a concise natural language comment for given snippet. Recently, the emergence of large models (LLMs) has led great boost performance processing tasks. Among them, ChatGPT is most popular one which attracted wide attention from engineering community. However, it still remains unclear how performs (automatic) summarization. Therefore, this...
Code search is a widely used technique by developers during software development. It provides semantically similar implementations from large code corpus to based on their queries. Existing techniques leverage deep learning models construct embedding representations for snippets and queries, respectively. Features such as abstract syntactic trees, control flow graphs, etc., are commonly employed representing the semantics of snippets. However, same structure these features does not...
Riparian zones act as critical "sinks" for nitrogen transformation and "buffers" removal in reservoirs. The operation of hydropower reservoirs significantly alters water levels these impacts the biogeochemical nitrogen. This is primarily driven by bacteria residing sediments riparian zones. However, impact level alteration on bacterial community its nitrogen-transformation function remains unclear. study investigates whether changes contents or water-level fluctuations resulting from...
Abstract This article examines citizen scoring in China's Social Credit Systems (SCSs). Focusing on 50 municipal cases that potentially cover 210 million population, we analyze how state actors quantify social and economic life into measurable comparable metrics discuss the implications of SCSs through lens quantification. Our results illustrate are envisioned designed as quantification practices including two facets: a normative apparatus encouraging “good” citizens morality, regulative...
The website security is an important issue that must be pursued to protect Internet users. Traditionally, blacklists of malicious websites are maintained, but they do not help in the detection new websites. This work proposes a machine learning architecture for intelligent detecting URLs. Forty-one features URLs extracted from data processes domain, Alexa and obfuscation. ANOVA (Analysis Variance) test XGBoost (eXtreme Gradient Boosting) algorithm used identify 17 most features. Finally,...
The server-aided encryption is widely used in encrypted deduplication systems to protect against brute-force attacks. However, it non-trivial update the master key managed by server existing schemes. Once leaked, all user data are vulnerable offline In this article, we extend with updatable (UE) and a dynamic proof of ownership (PoW) protocol make support efficient updates can be client-side deduplication. Specifically, design an scheme based on UE, which achieves user-transparent for...
(Source) code summarization is the task of automatically generating natural language summaries for given snippets. Such play a key role in helping developers understand and maintain source code. Recently, with successful application large models (LLMs) numerous fields, software engineering researchers have also attempted to adapt LLMs solve tasks. The main adaptation schemes include instruction prompting task-oriented fine-tuning. However, involves designing crafted prompts zero-shot...
(Source) code summarization aims to automatically generate succinct natural language summaries for given snippets. Such play a significant role in promoting developers understand and maintain code. Inspired by neural machine translation, deep learning-based techniques widely adopt an encoder-decoder framework, where the encoder transforms snippets into context vectors, decoder decodes vectors summaries. Recently, large-scale pre-trained models source are equipped with encoders capable of...
Programming language understanding and representation (a.k.a code learning) has always been a hot challenging task in software engineering. It aims to apply deep learning techniques produce numerical representations of the source features while preserving its semantics. These can be used for facilitating subsequent code-related tasks. The abstract syntax tree (AST), fundamental feature, illustrates syntactic information widely learning. However, there is still lack systematic quantitative...
While a lot of works have been proposed to smartly adapt quality video streaming services, none them involves the mechanism adaptive media playout, which could lead better performance in both user experience service and effectiveness radio resource. In this paper, an playout assisted rate adaptation scheme (AMP-RA) is improve over LTE systems. Firstly, optimization problem formulated, aims at maximizing subject constraints continuity amount available Moreover, two-step method solve problem....
HyperText Transfer Protocol (HTTP) adaptive streaming (HAS) has undoubtedly become the most cost-effective solution in delivering video contents over IP networks. While many works have been proposed to improve performance of HAS, HAS cellular networks is still a challenging problem due limited radio resource and dramatically increasing need for mobile service. Specifically, main comes from incongruous behaviors between rate adaptation allocation. The centralized scheme good choice solve this...
In order to overcome the shortcomings of current personal data applications in querying and matching, we adopt Web Ontology Language (OWL) for a uniform representation construct Personal Data Management Architecture various web applications. The description can not only provide efficiency exchange, but also flexibility management. Both sharing accurate information extraction be easily achieved by using Ontology. architecture consists Query Match Subsystem, Manager, Repository. Initially, all...
The broadcast scheme is a basic and important data dissemination mechanism in FANET. In this paper, we propose an efficient neighbor quality based mMultil- Ppoint Rrelay (MPR) on local status. status includes two aspects, i.e., the physical link congestion indicated by expected successful packet delivery ratio expiration time calculated from Received Signal Strength Indication (RSSI). determined queue length of each neighboring nodes. Then MPR set can be selected one-hop neighbors Each node...
In the mobile environment, users will use devices to enjoy different services, such as surfing Internet, shopping online, or paying bills. And network latency greatly affect performance of which influences using experience at same time. Many service selection methods have treated QoS, but they do not consider issue user's mobility that resulting inconstantly changing when existing information transmission between user and services in environment. So it is meaningful take into consideration...
Nowadays, HTTP adaptive streaming (HAS) has become a cost-effective solution in delivering the video content.Different from one-client HAS, HAS over multi-client faces many challenges. Due to lack of knowledge networks, will leads low efficiency utili
Reusing off-the-shelf code snippets from online repositories is a common practice, which significantly enhances the productivity of software developers. To find desired snippets, developers resort to search engines through natural language queries. Neural models are hence behind many such engines. These based on deep learning and gain substantial attention due their impressive performance. However, security aspect these rarely studied. Particularly, an adversary can inject backdoor in neural...