Hey👋 I am currently pursuing a Bachelor of Technology degree in Computer Science and Engineering at D.Y. Patil International University, set to graduate in 2025. My academic and research journey has been driven by a deep-seated passion for Artificial Intelligence and its applications, particularly in Natural Language Processing (NLP), Human-Computer Interaction (HCI), and AI alignment. I have consistently sought opportunities to contribute meaningfully to cutting-edge research, immersing myself in projects that bridge theoretical insights with real-world applications.

At present, I am actively involved in two exciting research projects. At the Indian School of Business, I am developing an advanced NLP pipeline combining OCR, text classification, and token classification models to analyze communal violence news articles. This involves fine-tuning state-of-the-art instructional large language models on a carefully curated synthetic dataset to achieve highly precise and structured outputs. Concurrently, I am contributing to a project at CISPA Helmholtz Center for Information Security in Germany, where I am auditing differentially private diffusion models. This work involves implementing differential privacy stochastic gradient descent (DPSGD) algorithms and designing innovative auditing mechanisms to evaluate privacy strictness in state-of-the-art diffusion models. These projects allow me to delve deeply into the nuances of privacy-preserving AI and the ethical dimensions of machine learning technologies.

My experience in research spans several years, starting with an internship at the National Institute of Technology Patna in 2022, where I optimized quadrupedal locomotion systems, followed by roles in academia and industry. Over this period, I have honed my skills in deep learning, model optimization, and privacy frameworks, culminating in impactful contributions to NLP, privacy-preserving AI, and big data analytics. These diverse experiences reflect my commitment to advancing research responsibly and ethically, as I work towards a future in which AI technologies are both innovative and inclusive.

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 Information Processing