I am a 3rd year Ph.D. student in Computer Science at the University of Vermont and a research scientist at OpenMined. I am very fortunate to be advised by Joe Near. My research interests broadly revolve around data privacy and all aspects of machine learning; theory, algorithms, and applications.
Currently, I’m focusing on private data analytics and privacy-preserving machine learning including differential privacy, federated learning, and secure multiparty computation.
In the past, I’ve published papers in fairness workshops at Neurips , contributed to Microsoft Research VowpalWabbit opensource project and to OpenMined’s PySyft library where we build Privacy Enhancing Technologies (PETs) that will hopefully lower the barrier of entry to privacy.
Fun fact: I’m a true citizen of the world! I’ve hopped across three continents for my education – the journey started with my undergrad in Cameroon, my Master’s degree brought me to Turkey, and now I’m crushing it in the land of the stars and stripes, the good ol’ USA!. Talk about racking up those frequent flyer miles!
Interested in collaborating? If you have a cool idea and would like to discuss it, don’t hesitate to email me.
News
-
December 2023: I am a program committee member for - The Fifth AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-24)
-
November 2023: I delivered an invited talk at Tumult Labs on our paper: Evaluating the Usability of Differential Privacy Tools with Data Practitioners
-
September 2023: New paper on arxiv: Evaluating the Usability of Differential Privacy Tools with Data Practitioners
-
September 2023: I gave a invited talk on "Privacy Preserving Machine Learning" to the UVM board of directors
-
August 2023: Two of our papers accepted at TPDP 2023
-
July 2023: I am an ethics reviewer for NeurIPS 2023
-
July 2023: Our new technical blogpost: How To Audit An AI Model Owned by Someone else (Part 1) posted on OpenMined
-
June 2023: I graduated from OpenMined's immersive Padawan Program
-
May 2023: I am a program committee member of the first Generative AI+Law - GenLaw workshop at ICML 2023
-
Febraury 2023: New paper on arxiv: OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols
-
Febraury 2023: Our paper Different Deep Learning Based Classification Models for COVID-19 CT-Scans and Lesion Segmentation Through the cGAN-UNet Hybrid Method got accepted at Traitement du Signal Journal
-
Febraury 2023: I am giving a talk on "Privacy Preserving Machine Learning" in Factored Learning Fest
-
December 2022: I am a volunteer at the Women in Machine Learning Workshop (WiML) held at NeurIPS2022
-
August 2022: I am giving a talk on my summer RLOS Microsoft Research project: Compiler optimization for Reinforcement Learning
-
June & August 2022: ML Oxford Summer ML : ML x Fundamentals Track & ML x Finance Track
-
June 2022: Differential Privacy summer school , Boston
-
June 2022: Our paper 'Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers' featured on Montreal AI Ethics
-
June 2022: Joined core team in Openmined as Research Scientist
-
May 2022: Gave a talk on Privacy and Fairness in AI at the University of Buea
-
Feb 2022: New paper on arxiv: Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers
-
Feb 2022: Co-organzing Differential Privacy Reading Group at UVM
-
Oct 2021: Presented our paper Feature Extraction Methods for Predicting the Prevalence of Heart Disease at the 6th International Conference on Smart City Applications
-
Sept 2021: Accepted for Google’s CS Research Mentorship Program
-
Aug 2021: Started PhD at the University of Vermont