A5100423030- Advanced Malware Detection Techniques
- Software Testing and Debugging Techniques
- Security and Verification in Computing
- Speech and Audio Processing
- Software Engineering Research
- Speech Recognition and Synthesis
- Time Series Analysis and Forecasting
- Digital and Cyber Forensics
- Adaptive Control of Nonlinear Systems
- Forecasting Techniques and Applications
- Inertial Sensor and Navigation
- Green IT and Sustainability
- Mobile and Web Applications
- Advanced Text Analysis Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Traffic Prediction and Management Techniques
- Stability and Control of Uncertain Systems
- Network Security and Intrusion Detection
- Music and Audio Processing
- Autonomous Vehicle Technology and Safety
- Neural Networks and Applications
- IoT and Edge/Fog Computing
- Anomaly Detection Techniques and Applications
Communication University of China
2022
Iowa State University
2009
Model-based test (MBT) generation techniques for automated GUI testing are of great value app testing. Existing model-based tools may fall into cyclic operations and run out resources, when applied to apps with industrial complexity scalability. In this work, we present a multi-agent MBT system named Fastbot. Fastbot performs model construction on the server end. It applies collaboration mechanism speed up procedure. The proposed approach was more than 20 applications from Bytedance 1500...
Android, the most popular mobile system, offers a number of user-configurable system settings (e.g., network, location, and permission) for controlling devices apps. Even popular, well-tested apps may fail to properly adapt their behaviors diverse setting changes, thus frustrating users. However, there exists no effort systematically investigate such defects. To this end, we conduct <i>first</i> large-scale empirical study understand characterize these <i>system setting-related defects</i>...
Virtual devices based on device emulation have been widely used in lab research of mobile app testing for their efficiency and low cost. However, it remains controversial to use virtual industry, given the inherent difficulties high-fidelity across diverse systems devices. Hence, companies still rely physical farms or services like AWS Device Farm.
Automated GUI testing has been playing a key role to uncover crashes ensure the stability and robustness of Android apps. Recent research proposed random, search-based model-based techniques for event generation. In industrial practices, different companies have developed various exploration tools such as Facebook Sapienz, WeChat WeTest ByteDance Fastbot test their products. However, these are bound predefined strategies lack ability generate human-like actions meaningful scenarios. To...
Android Apps are frequently updated to keep up with changing user, hardware, and business demands. Ensuring the correctness of App updates through extensive testing is crucial avoid potential bugs reaching end user. Existing tools generate GUI events that focus on improving test coverage entire rather than prioritising impacted elements. Recent research has proposed change-focused but relies random exploration exercise change-impacted elements ineffective slow for large complex a huge input...
Multivariate Time Series (MTS) widely exists in real-word complex systems, such as traffic and energy making their forecasting crucial for understanding influencing these systems. Recently, deep learning-based approaches have gained much popularity effectively modeling temporal spatial dependencies MTS, specifically Long-term Forecasting (LTSF) Spatial-Temporal (STF). However, the fair benchmarking issue choice of technical been hotly debated related work. Such controversies significantly...
Conventional approach of detecting malwares relies on static scanning malware signature. However, it may not work the that use software protection methods such as encryption and packing with run-time decryption unpacking. We propose a hardware-assisted detection system detects during program run time to complement conventional approach. It searches for control flow-based signature execution, therefore bypassing method used by those malwares. A new hardware design is assist collection flow...
In recent years, the development of advanced driver assistant system (ADAS) and vehicular communication has enhanced level autonomous vehicles connected vehicles, which brings a new security challenge to intelligent vehicles. This paper reviews existing vehicle-related threat modeling presents abstract model referring fundamental factors. Then we perform vulnerability analysis from three respects terminal, network communication, telematics system. Our work can provide comprehensive...
Most of traditional singing voice separation methods usually assume that the vocal model is source-filter thatextracts transfering functions vibration source and filters separately. In recent years, with rapid development deep learning, end-to-end have become increasingly popular achieved better results. Deep neural networks are very useful for processing complex nonlinear data. However, such models large parameter sizes lack interpretability. this paper, we propose a novel which combine...
Multivariate Time Series (MTS) forecasting plays a vital role in wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS methods due to their state-of-the-art performance. However, recent works are becoming more sophisticated with limited performance improvements. This phenomenon motivates us explore the critical factors and design model that is as powerful STGNNs, but concise efficient. In this paper, we identify...