My research interests include malware analysis and APT attack detection, and deep learning for complicated application (such as PM2.5 prediction).

1. Malware Analysis

Analyzing the attack methods of malicious software and the code used in these attacks is an extremely important and challenging task. We execute malicious programs in a virtual machine and record their calling behavior [6], then proceed to classify the malware families [1,5,7,9]. Since many types of malware are derived by modifying existing malicious software, understanding their family lineage is highly helpful for understanding their malicious behaviors. Next, we explore the nature and actions of the malware [4,8], and use the MITRE ATT&CK knowledge framework to detect the malicious behaviors of the malware [5] as well as the corresponding code [3]. Finally, we use large language models (LLMs) to generate documentation reports on the malicious software, detailing its malicious behaviors [2].

1. “MITREtrieval: Retrieving MITRE Techniques From Unstructured Threat Reports by Fusion of Deep Learning and Ontology”, Yi-Ting Huang, R. Vaitheeshwari, Meng Chang Chen, et al., IEEE Transactions on Network and Service Management, May 2024.
2. “Unleashing Malware Analysis and Understanding with Generative AI”, Yeali Sun, Zhi-Kang Chen, Yi-Ting Huang, Meng Chang Chen, IEEE Security & Privacy May-Jun. 2024, pp. 12-23, vol. 22.
3.  “Attention-Based API Locating for Malware Techniques”, Guo-Wei Wong, Yi-Ting Huang, Ying-Ren Guo, Yeali Sun, Meng Chang Chen, IEEE Transactions on Information Forensics & Security, Novemeber 2023,
4. "TagSeq: Malicious Behavior Discovery Using Dynamic Analysis", Yi-Ting Huang, Yeali Sun and Meng Chang Chen, PLOS ONE, May 2022.
5. "Open Source Intelligence for Malicious Behavior Discovery and Interpretation", Yi-Ting Huang, Chi Yu Lin, Ying-Ren Guo, Kai-Chieh Lo, Yeali S. Sun, and Meng Chang Chen, IEEE Transactions on Dependable and Secure Computing, March-April 2022.
6. “Hardware-Assisted MMU Redirection for In-guest Monitoring and API Profiling”, Mike Hsiao, Yeali Sun, Meng Chang Chen, IEEE Transactions on Information Forensics & Security, January 2020.
7. “Integration of Static and Dynamic Analysis for Malware Family Classification with Composite Neural Network” Yao Saint Yen, Zhe Wei Chen, Ying Ren Gua, Meng Chang Chen, arXiv preprint arXiv: 1912.11249, 2019.
8.  “Tagging Malware Intentions by using Attention-based Sequence-to-Sequence Neural Network”, Yi-Ting Huang, Yu-Yuan Chen, Chih-Chun Yang, Yeali Sun, Shun-Wen Hsiao, Meng Chang Chen, ACISP 2019, Churchill, New Zealand, 2019. 
9. “ANTSdroid: Automatic Malware Family Behaviour Generation and Analysis for Android Apps”, Yeali Sun, Shun-Wen Hsiao and Meng Chang Chen, ACISP 2018, Wollongong, Australia, 2018.

2. Deep Learning Theory and Application in PM2.5 Prediction       

In the PM2.5 Prediction Project, we have completed the 1km*1km PM2.5 forecast for the next 4 to 72 hours across Taiwan. We applied the PM2.5 forecast across Taiwan, not only to verify the deep learning theories we proposed, but also to provide real, high-accuracy predictions or inferences of PM2.5. We explored the performance issues after combining multiple pre-trained deep learning models and found that there is a high probability that the new model created through the combination outperforms the individual components [5,6]. In our PM2.5 prediction, we identified some inadequacies in current deep learning theories, such as event detection [2], the SGI problem [1], and others. We also used satellite data to predict long-range transportation (foreign pollution) [4], sea-land breeze phenomena [3], and employed airboxes to detect sudden pollution (factory emissions, fires, etc.) [7].

1. “Sparse Grid Imputation Using Unpaired Imprecise Auxiliary Data: Theory and Application to PM2.5 Estimation”, Ming-Chuan Yang, Guo Wei Wong, Meng Chang Chen, ACM Transactions on Knowledge Discovery from Data, January 2024.
2. "Extreme Event Discovery with Self-Attention for PM2.5 Anomaly Prediction," Hsin-Chih Yang, Ming-Chuan Yang, Guo Wei Wong, Meng Chang Chen, IEEE Intelligent Systems, January 2023.
3. "Influence of Land-Sea Breeze on PM 2.5 Prediction in Central and Southern Taiwan Using Composite Neural Network", GW Kibirige, CC Huang, CL Liu, MC Chen, Scientific Reports, 13 (1), 3827, 2023
4. “Using Satellite Data on Remote Transportation of Air Pollutants for PM2.5 Prediction in Northern Taiwan”, George William Kibirige, Ming-Chuan Yang, Chao-Lin Liu, Meng Chang Chen, PLOS ONE, March 2023.
5. “Composite Neural Network: Theory and Application to PM2.5 Prediction”, Ming-Chuan Yang, Meng Chang Chen, IEEE Transactions on Knowledge and Data Engineering, July 2021.
6. “PM2. 5 Forecasting Using Pre-trained Components”, Ming-Chuan Yang, Meng Chang Chen, 2018 IEEE International Conference on Big Data (Big Data), Seattle, 2018.
7.  “LOST: A Location Estimator Scheme for PM2.5 Pollution Sources in Sparse Sensors Network” Faisal Ghaffar, George William Kibirige, Chih-Ya Shen, and Meng Chang Chen, Globecom, 2020