我目前研究興趣包括： 惡意軟體分析與APT攻擊偵測、深度學習於PM2.5預測。

1. Malware Analysis

分析惡意軟體攻擊方式以及攻擊所用程式碼是一件極為重要也很困難的工作。我們以虛擬機方式來執行惡意程式並記錄其呼叫行為[6]，然後進行惡意軟體家族的分類[1,5,7,9]。因為惡意軟體多是修改既有惡意軟體而得之，所以知道其家族淵源對了解其惡意行為有很大幫助。接著我們探討惡意軟體的內涵與動作[4,8]，並根據MITRE ATT&CK的知識框架來偵測惡意軟體的惡意行為[5]，以及相對的程式碼[3]。我們使用LLM來產生惡意軟體的文件報告，詳述其惡意行為[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

在PM2.5預測計畫我們完成全台灣各地 1km*1km PM2.5未來4至72小時的預測。我們以全台灣PM2.5的預測為應用，不僅可驗證我們所提出深度學習的理論，並且可提供PM2.5真實、高準度之預測或推測。我們探討多個已訓練完成的深度學習模型組合後的效能問題，發現有很高的機率會存在組合後的新模型勝過其中個別元件[5,6]。並以PM2.5預測中發現目前深度學習理論不足處，例如突發事件偵測[2]，SGI問題[1]等。並且使用衛星資料來預測遠程輸送(境外汙染)[4]，海陸風現象[3]，以及以空氣盒子來偵測突發汙染(工廠排放、火災等)[ 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