Sep 2023 – Jan 2025 · 1 yr 4 mos · Boston, Massachusetts, United States · On-site

• Reviewed material, graded assignments, and conducted office hours for the courses: Introduction to Data Mining and Machine Learning and Foundations of AI.

Dec 2022 – Jul 2023 · 7 mos · Bengaluru, Karnataka, India

• Developed a cutting-edge privacy-preserving mean estimation algorithm, ensuring user-level privacy in a non-IID setting. Achieved exceptional results, surpassing existing approaches with a significant 20% increase in utility and an outstanding 36% enhancement in privacy.
• Designed a privacy-preserving approach for generative models based on quantization of latent space and exponential mechanism with differential privacy guarantees.

Feb 2022 – Jul 2022 · 5 mos

• Implemented a pipeline for federated neural collaborative filtering from scratch for recommendation systems.
• Integrated federated learning optimizers and aggregators.
• Undertook the development of end-to-end solutions with the dynamofl framework for diverse client use cases.

Oct 2021 – Dec 2021 · 2 mos

Aug 2021 – Oct 2021 · 2 mos

Aug 2021 – Jan 2022 · 5 mos · Kurukshetra, Haryana, India

• Created a data poisoning attack for collaborative learning settings, which resulted in a success rate that was over 3 times improvement over the existing error-generic attacks.
• Investigated the use of encoder based models in distributed learning to achieve cross-domain generalization of network intrusion in a multi-client setting.

Dec 2020 – Feb 2021 · 2 mos