Hey 👋 I’m an undergraduate student in Computer Science at D.Y. Patil International University, graduating in 2025. I’m deeply curious about AI and how we can build systems that are both powerful and trustworthy. My work mainly revolves around natural language processing (NLP), human-AI interaction, and privacy-preserving machine learning.

Currently, I’m involved in research at two places. At CISPA Helmholtz Center for Information Security, I’m working on auditing and improving privacy techniques for generative models, especially diffusion and autoregressive models. I’m also collaborating with the Indian School of Business, where I’m building NLP pipelines to analyze sensitive news data — combining large language models with tools like OCR and classification systems to structure messy real-world information.

Across these projects, I’m exploring how to make machine learning systems more private, reliable, and aligned with human values. My goal is to work at the intersection of ethics and cutting-edge AI, and contribute to systems that are not only smart but safe.

Current Research Projects

• Differentially Private Image Generation Models
• India Violence Archive

Research Interests

• Natural Language Processing
• AI Alignment
• Large Language Models
• Human-Computer Interaction (HCI)
• Adversarial Machine Learning
• Interpretability
• Privacy in ML
• Trustworthy ML