Publications

Publications

* denotes equal contribution.

2026
MOAT: Model-Agnostic Randomized Transformations to Prevent Efficiency Degradation Attacks on Vision Transformers
Anadi Goyal, Nandish Chattopadhyay, Chandan Karfa, Anupam Chattopadhyay, and Norrathep Rattanavipanon
IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 2026
Accepted [Paper]
STRAP-ViT: Segregated Tokens with Randomized-Transformations for Defense against Adversarial Patches in ViTs
Nandish Chattopadhyay, Anadi Goyal, Anupam Chattopadhyay, and Chandan Karfa
Design Automation Conference (DAC), 2026
Accepted [Paper]
2025
Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization: A Survey
Anadi Goyal, Nandish Chattopadhyay, Anupam Chattopadhyay, and Chandan Karfa
Artificial Intelligence and Internet of Things (AIIoT), 2025
Accepted [Paper]
HAVIT: An Efficient Hardware-Accelerator for Vision Transformer with Informative Patch Selection Techniques
Anadi Goyal, Gaurav Sangwan, Aradhya Patel, and Palash Das
ACM Transactions on Architecture and Code Optimization (ACM TACO), 2025
Published [Paper]
Enhanced Prefetching via Dynamic Multi-Step SARSA based Reinforcement Learning
Satyaswaroop Nayak, Anadi Goyal, Sheel Sindhu Manohar, Dip Sankar Banerjee, and Palash Das
IEEE Embedded Systems Letters (ESL), 2025
Published [Paper]
Hybrid Token Selector based Accelerator for ViTs
Akshansh Yadav*, Anadi Goyal*, and Palash Das
Design, Automation and Test in Europe (DATE), IEEE, 2025
Published [Paper] [Presentation]
Under Review
Secure Hardware Accelerator for Resilience Against Adversarial Attacks in ViTs
Deepraj Majumdar, Anadi Goyal, Sparsh Mittal, Shirshendu Das, and Palash Das
IEEE Transactions on Computers (TC)
Under Review — Final Round