Sukrit Jindal

Sukrit Jindal

Joint Secretary, DSG IIT Roorkee


Education

  • B.Tech, Data Science and Artificial Intelligence, IIT Roorkee (2022–2026)
  • Minor in Computer Science Engineering

Research Interests

  • Machine Learning and Deep Learning
  • Machine Learning Security, Interpretability and Robustness
  • Graph Neural Networks
  • AI for Cybersecurity

Projects

  • Diffusion Everything
    Developed visual demonstrations of diffusion processes using 2D/3D datasets and implemented DDPM/DDIM sampling techniques.
  • PikaBot RL
    Trained battle bots using reinforcement learning algorithms like DDQN for an online Pokémon battle simulator.
  • Steganography with GNNs
    Proposed an improved universal deep hiding technique using graph neural networks over traditional CNNs.
  • Web-Based Saliency Demos Explore the interpretability offered by various saliency-map based models like IG, BlurIG and VG and their extensions (IDGI and SmoothGrad).

Publications

  • Jindal, S., Bhardwaj, D., & Kumari, A. (2024). Rethinking Randomized Smoothing from the Perspective of Scalability. Third Workshop on New Frontiers in Adversarial Machine Learning (NeurIPS ‘24). (Co-Author)
  • Mittal, A., Pandey, A., Tiwari, A., Jindal, S., & Swain, S. (2025). Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models Under Review at TMLR 2025 (Co-Author)

GitHub | LinkedIn


Updated: