Shorya Singhal
Core Member, DSG IIT Roorkee
Education
- B.Tech, Data Science and Artificial Intelligence, IIT Roorkee (2022–2026)
Research Interests
- Graph Neural Networks
- Natural Language Processing
- Machine Learning Security
-
Generative Modelling
Projects
- Diffusion Everything
Developed visual demonstrations of diffusion processes using 2D/3D datasets and implemented DDPM/DDIM sampling techniques. - TransXGBoost
Developed algorithm for low light image restoration using XGBoost for histogram transformation and Vision Transformer for furthur filtering.
Publications
- Singhal, S., Badgujar P., & Bhardwaj, D. (2025). One Noise to Fool Them All : Universal Adversarial Defenses Against Image Editing The 5th Workshop of Adversarial Machine Learning on Computer Vision: Foundation Models + X at CVPR 2025 (Co-Author)