Caribbean sea
Caribbean sea from Cuba
Posts by Collection
portfolio
Aurora
Aurora from Iceland
Iceland
An image of Iceland landscape
Iceland plane?
Sorta famous site in Iceland
Sunset
Sunset shot from a parking lot near home
Milky Way
Milky way taken from a national park
Cloud Burning
Cloud burning taken at Saguenay
Park Mauricie
Fall in Mauricie
publications
Discourse Parsing with Attention-based Hierarchical Neural Networks
Published in EMNLP 2016, 2016
This paper is about our discourse parsing model
Recommended citation: Qi Li, Tianshi Li, and Baobao Chang. "Discourse Parsing with Attention-based Hierarchical Neural Networks." EMNLP. 2016. https://aclanthology.org/D16-1035.pdf
A Novel and Dedicated Machine Learning Model for Malware Classification
Published in ICSOFT 2021, 2021
This paper proposes a novel dedicated machine learning model for malware classification.
Recommended citation: Miles Q. Li, Benjamin CM Fung, Philippe Charland, and Steven HH Ding. "A Novel and Dedicated Machine Learning Model for Malware Classification." In ICSOFT, pp. 617-628. 2021. https://dmas.lab.mcgill.ca/fung/pub/LFCD21icsoft_postprint.pdf
A Novel Neural Network-Based Malware Severity Classification System
Published in International Conference on Software Technologies (Springer), 2021
This paper proposes a neural network-based malware severity classification method.
Recommended citation: Miles Q. Li and Benjamin CM Fung. "A Novel Neural Network-Based Malware Severity Classification System." In International Conference on Software Technologies, pp. 218-232. Springer, 2021. https://link.springer.com/chapter/10.1007/978-3-031-11513-4_10
Malware classification and composition analysis: A survey of recent developments
Published in Journal of Information Security and Applications, 2022
This paper is about our survey paper on malware detection
Recommended citation: Abusitta, Adel, Miles Q. Li, and Benjamin CM Fung. "Malware classification and composition analysis: A survey of recent developments." Journal of Information Security and Applications 59 (2021): 102828. https://www.sciencedirect.com/science/article/pii/S2214212621000648
DyAdvDefender: An instance-based online machine learning model for perturbation-trial-based black-box adversarial defense
Published in Journal of Information Sciences, 2022
This paper is about our novel black-box adversarial defense method
Recommended citation: Li, Miles Q., Benjamin CM Fung, and Philippe Charland. "DyAdvDefender: An instance-based online machine learning model for perturbation-trial-based black-box adversarial defense." Information Sciences (2022). https://www.sciencedirect.com/science/article/pii/S0020025522003747?casa_token=p5N50hWOf0oAAAAA:OoG3up9I8-W8kW1zutzK3zuzOZL1kpWspm_7h0YJZC_aowNcFvN97aUNwcWJvMX61QngMi4aNjy4
Interpretable Malware Classification based on Functional Analysis
Published in ICSOFT 2022, 2022
This paper proposes a novel interpretable malware classification model based on functional analysis.
Recommended citation: Miles Q. Li and Benjamin CM Fung. "Interpretable Malware Classification based on Functional Analysis." In ICSOFT, pp. 500-507. 2022. https://www.scitepress.org/Papers/2022/113109/113109.pdf
On the Effectiveness of Interpretable Feedforward Neural Network
Published in IJCNN 2022, 2022
This paper is about our novel interpretable feedforward neural network
Recommended citation: Li, M. Q., Fung, B. C. M., & Abusitta, A. On the Effectiveness of Interpretable Feedforward Neural Network. In Proceedings of the International Conference on Joint Conference on Neural Networks (IJCNN), pages 1-8, Padova, Italy: IEEE, July 2022. https://arxiv.org/pdf/2111.02303.pdf
I-MAD: Interpretable malware detector using Galaxy Transformer
Published in Journal of Computers & Security, 2022
This paper is about our novel malware detection model
Recommended citation: Miles Q. Li, Benjamin CM Fung, Philippe Charland, and Steven HH Ding. "I-MAD: Interpretable malware detector using Galaxy Transformer." Computers & Security 108 (2021): 102371. https://www.sciencedirect.com/science/article/pii/S0167404821001954
VDGraph2Vec: Vulnerability Detection in Assembly Code Using Message Passing Neural Networks
Published in ICMLA 2022, 2022
This paper proposes an automated deep learning method to generate representations of assembly code for vulnerability detection.
Recommended citation: Ashita Diwan, Miles Q. Li, and Benjamin CM Fung. "VDGraph2Vec: Vulnerability Detection in Assembly Code Using Message Passing Neural Networks." In 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 1039-1046. IEEE, 2022. https://ieeexplore.ieee.org/document/10069134/
A Novel Deep Multi-head Attentive Vulnerable Line Detector
Published in Procedia Computer Science, 2023
This paper proposes a hybrid neural network combining memory networks and multi-head attention for detecting vulnerable lines of code.
Recommended citation: Miles Q. Li, Benjamin CM Fung, and Ashita Diwan. "A Novel Deep Multi-head Attentive Vulnerable Line Detector." Procedia Computer Science 222 (2023): 35-44. https://www.sciencedirect.com/science/article/pii/S1877050923009079
Survey on Explainable AI: Techniques, challenges and open issues
Published in Journal of Expert Systems with Applications, 2024
This paper is about our survey paper on explainable AI
Recommended citation: Abusitta, Adel, Miles Q. Li, and Benjamin CM Fung. "Survey on Explainable AI: Techniques, challenges and open issues." Expert Systems with Applications (2024): 124710. https://www.sciencedirect.com/science/article/pii/S095741742401577X
On the Effectiveness of Incremental Training of Large Language Models
Published in arXiv preprint / Under review for International Journal of Data Science and Analytics, 2024
This paper investigates the effectiveness of incremental training strategies for large language models.
Recommended citation: Miles Q. Li, Benjamin Fung, and Shih-Chia Huang. On the Effectiveness of Incremental Training of Large Language Models. arXiv preprint arXiv:2411.18700 (2024). https://arxiv.org/abs/2411.18700
Training Dynamics of a 1.7B LLaMa Model: A Data-Efficient Approach
Published in IJCNN 2025, 2025
This paper is about our study on training a 1.7B LLaMa model
Recommended citation: Miles Q. Li, Benjamin CM Fung, and Shih-Chia Huang. Training Dynamics of a 1.7B LLaMa Model: A Data-Efficient Approach. In Proceedings of the International Conference on Joint Conference on Neural Networks (IJCNN), pages 1-10, Roma, Italy: IEEE, June 2025. https://arxiv.org/abs/2412.13335
Security Concerns for Large Language Models: A Survey
Published in Journal of Information Security and Applications, 2025
This paper is about our study on the security concerns with LLMs
Recommended citation: Miles Q. Li, and Benjamin CM Fung. Security Concerns for Large Language Models: A Survey. Journal of Information Security and Applications 95 (2025): 104284. https://www.sciencedirect.com/science/article/pii/S2214212625003217?casa_token=8Ce8QlKHMEoAAAAA:Dy_eO6f0zDbNjuXcwnPBnT9ezs0QQu8Ne_sn1DThh55aw4u-QP4OL0PbOIWzlL_ydi8uhlsP4w
A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
Published in arXiv preprint / Under review for ICML 2026, 2025
This paper presents ODCV-Bench, a safety benchmark for evaluating constraint violations in autonomous AI agents.
Recommended citation: Miles Q. Li, Benjamin Fung, Martin Weiss, Pulei Xiong, Khalil Al-Hussaeni, and Claude Fachkha. A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents. arXiv preprint arXiv:2512.20798 (2025). https://arxiv.org/abs/2512.20798
GPT-based Self-supervised Anomaly Detection in Command Lines
Published in Journal of Computer Virology and Hacking Techniques, 2026
This paper is about our GPT-based self-supervised anomaly detection system for command lines
Recommended citation: Miles Q. Li, Julien Keutchayan, François Charest, and Benjamin C.M. Fung. GPT-based Self-supervised Anomaly Detection in Command Lines. Journal of Computer Virology and Hacking Techniques, Springer, 2026.
talks
Generative AI Model for Security
Published:
Invited presentation at the IVADO Community of Practice at HEC Montreal. Presented research on generative AI models for security to the IVADO research community.
Security Concerns for Large Language Models
Published:
Invited talk on security concerns for large language models at Kean University. (Upcoming)
teaching
Teaching assistant of Java Program Design
Undergraduate course, Peking University , School of EE&CS, 2026
Teaching assistant of the course on the online platforms for Java programming
Teaching assistant of Computational Linguistics
Graduate course, Peking University , School of EE&CS, 2026
Teaching assistant of the graduate course Computational Linguistics
Teaching assistant of Foundations of Computer Application
Undergraduate course, Peking University , School of EE&CS, 2026
Teaching assistant of the undergraduate course Foundations of Computer Application