Discourse Parsing with Attention-based Hierarchical Neural Networks
Qi Li, Tianshi Li, and Baobao Chang. "Discourse Parsing with Attention-based Hierarchical Neural Networks." EMNLP. 2016.
CV
Education
- Ph.D. in Computer Science, McGill University, 2022
- Supervisor: Prof. Benjamin C.M. Fung
- Thesis: Interpretable Machine Learning for Malware Detection and Adversarial Defense
- Focus: Deep Learning and Data Mining for Cybersecurity
- GPA: 4.0/4.0
- M.S. in Computer Software and Theory, Peking University, 2017
- Supervisor: Prof. Baobao Chang
- Thesis: Document-Level Semantic Analysis Using Hierarchical Long Short-Term Memory Networks
- Focus: Natural Language Processing and Deep Learning
- B.S. in Physics, Peking University, 2014
Work experience
- Postdoctoral Researcher, McGill University (2022–2024, 2025–present)
- Research on the security, safety, and trustworthiness of AI systems. Proposed a novel taxonomy of LLM security threats. Authored peer-reviewed research papers in leading AI & security journals and conferences. Developed a benchmark for evaluating safety constraint violations in autonomous AI agents. Built a LLM-based self-supervised anomaly detection system for cybersecurity applications.
- AI Research Content Educator/Consultant, Infinite Optimization AI Lab (2024–2025)
- Creating technical videos explaining LLMs, NLP, and deep learning concepts. Providing consulting service to AI researchers and engineers.
- Consultant Research Intern, MITACS Internship at Desjardins Group (2022–2024)
- Developed a state-of-the-art LLM-based anomaly detection system for identifying and explaining malicious command lines in a financial institution’s cybersecurity infrastructure.
Skills
- Python (PyTorch, Hugging Face, LangChain/LangGraph)
- Java
- Docker
- LLM pretraining, fine-tuning, and alignment
- Multi-agent system architecture
Publications
A Novel and Dedicated Machine Learning Model for Malware Classification
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.
A Novel Neural Network-Based Malware Severity Classification System
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.
Malware classification and composition analysis: A survey of recent developments
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.
DyAdvDefender: An instance-based online machine learning model for perturbation-trial-based black-box adversarial defense
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).
Interpretable Malware Classification based on Functional Analysis
Miles Q. Li and Benjamin CM Fung. "Interpretable Malware Classification based on Functional Analysis." In ICSOFT, pp. 500-507. 2022.
On the Effectiveness of Interpretable Feedforward Neural Network
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.
I-MAD: Interpretable malware detector using Galaxy Transformer
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.
VDGraph2Vec: Vulnerability Detection in Assembly Code Using Message Passing Neural Networks
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.
A Novel Deep Multi-head Attentive Vulnerable Line Detector
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.
Survey on Explainable AI: Techniques, challenges and open issues
Abusitta, Adel, Miles Q. Li, and Benjamin CM Fung. "Survey on Explainable AI: Techniques, challenges and open issues." Expert Systems with Applications (2024): 124710.
On the Effectiveness of Incremental Training of Large Language Models
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).
Training Dynamics of a 1.7B LLaMa Model: A Data-Efficient Approach
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.
Security Concerns for Large Language Models: A Survey
Miles Q. Li, and Benjamin CM Fung. Security Concerns for Large Language Models: A Survey. Journal of Information Security and Applications 95 (2025): 104284.
A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
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).
GPT-based Self-supervised Anomaly Detection in Command Lines
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
Invited Presentation at IVADO Community of Practice, HEC Montreal, Montreal, Canada
Security Concerns for Large Language Models
Invited Talk at Kean University, USA
Teaching
Service
Journal Reviewing
- Nature Communications, Springer (Co-reviewer as an Early Career Researcher)
- Artificial Intelligence Review, Springer
- Computers & Security, Elsevier
- Expert Systems with Applications, Elsevier
- International Journal of Information Security, Springer
- Open Journal of the Communications Society, IEEE
- Sustainable Cities and Society, Elsevier
- The Journal of Supercomputing, Springer
- Journal of Computer Virology and Hacking Techniques, Springer
- Journal of Cyber Security Technology, Taylor & Francis
- Cluster Computing, Springer
- Pattern Recognition Letters, Elsevier
- Journal of Big Data, Springer
- EURASIP Journal on Information Security, Springer
- Discover Artificial Intelligence, Springer
- IEEE Access, IEEE
Conference Reviewing
- AISTATS (2022, 2023, 2025 — Best Reviewer Award)
- IJCNN (2023, 2024, 2025)
- EMNLP (2017, 2018)
- CoNLL (2017)
Secondary Reviewing
- ICDM (2018, 2019, 2021), CIKM (2017, 2018, 2020), AAAI (2018, 2020), SDM (2018), IJCAI (2019), CCKS (2017), ICCPOL (2016)
Leadership
- 2012–2013: President of Open-source Software Association, Peking University