Curriculum Vitae

Anadi Goyal

Research Assistant · IIT Guwahati

anadigoyal05@gmail.com · anadigoyal@rnd.iitg.ac.in

anadigoyal.github.io

↓ Download PDF
Research Interests

Efficient and accelerator-aware AI inference · Hardware acceleration of deep learning models · Adversarial robustness and AI security.

Education
B.Tech. in Mechanical Engineering
Indian Institute of Technology Jodhpur
Dec 2021 – June 2025
GPA: 7.81
Senior Secondary
Surbhi Senior Secondary School, RBSE
2020
89.6%
Work Experience
Research Assistant
Dept. of CSE, IIT Guwahati
Supervisors: Dr. Chandan Karfa (IIT Guwahati) & Dr. Anupam Chattopadhyay (NTU Singapore)
  • Developed model-agnostic defenses for adversarial patch attacks on Vision Transformers.
  • Analyzed efficiency-targeted adversarial attacks exploiting optimization strategies in ViTs.
  • Proposed approaches to enhance robustness of optimized/accelerated ViT inference pipelines.
  • Investigating energy-based attacks on efficient AI inference hardware.
  • Improving robustness of LLMs against jailbreak prompts.
July 2025 – present
Publications
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
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
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
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
Hybrid Token Selector based Accelerator for ViTs
Akshansh Yadav*, Anadi Goyal*, and Palash Das
Design, Automation and Test in Europe (DATE), IEEE, 2025
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
Teaching Experience
Teaching Assistant — Python for Data Engineering
IIT Jodhpur, under Dr. Palash Das and Dr. Bikash Santra
  • Set up Python assignments and organized lab sessions.
  • Mentored a group of 30 students with periodic discussions and feedback sessions.
Fall 2023 & 2024
Skills
Languages
C, C++, Python, HTML+CSS
Tools
Xilinx Vivado, Xilinx Vitis HLS, LaTeX
Frameworks
PyTorch, TensorFlow, Pynq, Qiskit
Awards & Grants
IEEE CEDA Travel Grant
INR 1,30,000 (~$1500) to present research at DATE 2025, France
2025
VLSID 2025 Fellowship
Awarded fellowship to attend VLSID 2025
2025