Scholar
Gaurang Sriramanan
Google Scholar ID: t76Uk8oAAAAJ
PhD Student, University of Maryland, College Park
Citations & Impact
Citations
497
H-index
8
i10-index
8
Publications
13
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including 'LLM-Check: Investigating Detection of Hallucinations in Large Language Models' (NeurIPS 2024) and 'Fast Adversarial Attacks on Language Models In One GPU Minute' (ICML 2024). Received Outstanding Reviewer Awards at CVPR 2022, ECCV 2022, and ICLR 2023, and served as a reviewer for several international conferences and journals.
Research Experience
- Conducted research at the Computational and Data Sciences Department and the Mathematics Department at IISc before joining UMD. Currently working on developing efficient attacks and robust training techniques that minimize computational overhead.
Education
- PhD in Computer Science from University of Maryland (UMD), advised by Prof. Soheil Feizi; Bachelor's and Master's degrees in Mathematics from Indian Institute of Science (IISc), Bangalore, advised by Prof. Venkatesh Babu and Prof. Kaushal Verma.
Background
- A fourth-year Computer Science PhD student, focusing on improving the reliability, security, and robustness of Deep Neural Networks. Enthusiastic about understanding the over-sensitivity of modern Vision models and Large Language models to adversarial or jailbreaking inputs, as well as their under-sensitivity to blind spots. Recently, investigating hallucinations in Large Language Models and strategies for detecting them in real-world production settings.
