About / Bio
I am a PhD candidate in the Computer Science Department at the University of California, Davis, being advised by Prof. Prasant Mohapatra. My research primarily focuses on improving Machine Learning (ML) models to further facilitate their adoption into society by analyzing model robustness along two dimensions: (i) adversarial robustness (adversarial attacks/defenses against learning models) and (ii) social robustness (fair machine learning and trustworthy AI).
I am also interested in other applied problems such as (i) designing learning based debiasing interventions for social media platforms (YouTube/Twitter, among others) and (ii) ML based approaches for improving networked systems. I am also the author of the Tensorflex framework (NeurIPS 2018 presented paper link). From time to time, I write technical articles on my blog, so if interested do have a look here.
9/14/2022: Our paper "On the Robustness of Deep Clustering Models: Adversarial Attacks and Defenses" was accepted at the NeurIPS 2022 Main Conference [pdf] [code]
9/17/2021: Our survey paper on fairness in clustering was accepted for publication in IEEE Access [pdf]
1/25/2019: Invited to talk about our research on adversarial attacks against clustering at Uber AI in SF by Ryan Turner