📄 Preprints and Workshop Papers
Agent Communication Protocols Enhance Collective Inference
Devansh Bhardwaj, Arjun Beniwal, Shreyas Chaudhari, Ashwin Kalyan, Tanmay Rajpurohit, Karthik R Narasimhan, Ameet Deshpande, Vishvak Murahari
Preprint
[arXiv] [Project Page]
One Noise to Fool Them All: Universal Adversarial Defenses Against Image Editing
Devansh Bhardwaj, Parth Badgujar, Shorya Singhal
AdvML Workshop @ CVPR 2025
[Paper]
Rethinking Randomized Smoothing from the Perspective of Scalability
Devansh Bhardwaj, Anupriya Kumari, Sukrit Jindal
AdvML Workshop @ NeurIPS 2025
[arXiv]
Invisible Traces: Using Hybrid Fingerprinting to identify underlying LLMs in GenAI Apps
Devansh Bhardwaj, Naman Mishra
Preprint
[arXiv]
Video Generation with Learned Action Prior
M. Sarkar, D. Bhardwaj, D. Ghose
Preprint
[arXiv] [Code]
Accelerated Smoothing: A Scalable Approach to Randomized Smoothing
Devansh Bhardwaj, Kshitiz Kaushik, Sarthak Gupta
Preprint
[arXiv] [Code]