Syed Moiz Ali

Syed Moiz Ali

CS Ph.D. Student at UIC

About

I am a second-year Ph.D. Computer Science student at University of Illinois Chicago (UIC), advised by Jason Polakis.

I completed my undergrad in Computer Science at LUMS, where I had the good fortune of being advised by Ashish Gehani, Sazzadur Rahaman, Yasir Zaki, and Fareed Zaffar. My undergraduate research focused on the alignment of large language models (LLMs) for security and on auditing and improving program analysis techniques.

I am broadly interested in the use of LLMs, particularly browsing agents on the internet. My current research focuses on auditing these agents for security, focusing on fingerprinting and privacy risks. Through this work, I aim to help developers and researchers identify security and privacy risks and build more robust systems.

Publications

  1. AgentShield: Fortifying Web Applications Against AI Agents and Agentic Browsers
    Moiz Ali*, Nafis Karim*, Rownak Islam, Jyotirmay Chauhan, Dhruv Kuchhal, Jason Polakis
    IEEE Symposium on Security and Privacy (S&P), 2027
    Abstract · Paper

  2. Data Doping or True Intelligence? Evaluating the Transferability of Injected Knowledge in LLMs
    Essa Jan*, Moiz Ali*, Saram Hassan, Fareed Zaffar, Yasir Zaki
    Findings of the Association for Computational Linguistics: EMNLP, 2025
    Paper

  3. MultitaskBench: Unveiling and Mitigating Safety Gaps in LLM Fine-tuning
    Essa Jan, Nouar AlDahoul, Moiz Ali, Faizan Ahmad, Fareed Zaffar, Yasir Zaki
    International Conference on Computational Linguistics (COLING), 2025
    Paper · Code

* Equal contribution

News