Stanford UniversityAbout me
Machine learning researcher focused on evaluating and improving the reliability of LLMs. I develop benchmarks for testing AI systems on complex reasoning tasks, particularly in legal domains like unemployment insurance adjudication and statutory analysis across multiple jurisdictions. I have extensive research experience working on model vulnerabilities including backdoor attacks, and adversarial robustness in both NLP and Computer Vision.
Recent News
Jun. 2025: I presented our paper on efficent image encoding for QNNs at CVPR 2025.
Dec. 2024: I presented our paper on LLMs Empowering Phishing Attacks at IEEE Big Data.
Nov. 2024: Fordham News published an article covering my interview on our lead research.
Oct. 2024: Our paper on optimizing lead testing for children in NYC was published by The Journal of Urban Health.
Sep. 2024: I presented our paper on Imbalanced Datasets at the 28th KES conference.
April. 2024: I won the third place award at the Fordham Three Minute Thesis Competition for our research paper on Lead Testing for Childeren in New York City. [Competition Results]
May. 2023: I was featured by the U.S. Embassy Mauritania Facebook page after finishing my master’s degree as part of the Fulbright Program [Post]
Publications
Machine Learning for Public Health
M. Afane and J. Chen, “Analyzing and Optimizing the Distribution of Blood Lead Level Testing for Children in New York City”, Journal of Urban Health 2024, [Paper].
M. Afane, Y. Wang, and J. Chen, “Can LLMs Help Allocate Public Health Resources? A Case Study on Childhood Lead Testing”, Accepted at IEEE BigData 25.
Quantum Machine Learning
M. Afane, G. Ebbrecht, Y. Wang, J. Chen, and J. Farooq. “ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networkss”, CVPR 2025. [Paper]
M. Afane, K. Laufer, W. Wei, Y. Mao, J. Farooq, Y. Wang, and J. Chen. “Benchmarking Large Language Models Quantum Computing Knowledge”, Submitted to ICLR 2026.
M. Afane, Q. Long, H. Shen, Y. Mao, and J. Chen. “Quantum Architecture Optimization for Adversarial Robustness.”, Submitted to Quantum Machine Intelligence.
Modern Challenges in AI and Data Science
M. Afane, W. Wei, Y. Mao, and J. Chen, “Next-Generation Phishing: How LLM Agents Empower Cyber Attackers”, IEEE BigData 2024. [Paper].
M. Afane and Y. Zhao, “Selecting Classifiers and Resampling Techniques for Imbalanced Datasets: A New Perspective”, 28th International KES 2024.[Paper].
M. Afane, J. Chen, et al. “SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models”. Accepted at IEEE BigData 25.