About me

I am a third-year PhD student at the University Of Chicago in the department of Computer Science. I am being advised by Professor Michael Maire.
My current research has been in designing improved pretraining techniques for MoE based LLMs. I am interested in designing architectures which can improve training efficiency and model performance. I'm also working on developing a framework for boosting deep learning models by efficiently finding the most useful data in external datasets using supervised and unsupervised algorithms. This framework can be used to valuelarge-scale private datasets in data markets. In the past, I've worked on detecting text generated by LLMs, video and virtual reality based keystroke inference attacks and designing voice anonmyzing tools to prevent against voice cloning attacks.
And before that, I was interested in auction theory as an Economics major.

Publications

Can Virtual Reality Protect Users from Keystroke Inference Attacks?
Zhuolin Yang, Zain Sarwar, Iris Hwang, Ronik Bhaskar, Ben Y. Zhao, Haitao Zheng
Proceedings of USENIX Security Symposium
Philadelphia, PA, August 2024.
PDF Project Webpage

Towards a General Video-based Keystroke Inference Attack
Zhuolin Yang, Yuxin Chen, Zain Sarwar, Hadleigh Schwartz, Ben Y. Zhao, Haitao Zheng
Proceedings of USENIX Security Symposium
Anaheim CA, August 2023.
PDF Project Webpage

Deepfake Text Detection: Limitations and Opportunities
Jiameng Pu*, Zain Sarwar*, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, and Bimal Viswanath
IEEE S&P (Oakland) 2023, San Francisco, CA, May 2023.
PDF Video Code and Dataset