Debopam Sanyal

I am a PhD student in Computer Science [SCS] at Georgia Institute of Technology, where I specialize in machine learning and systems under the supervision of Prof. Alexey Tumanov. My current research interests are in efficient and private machine learning at the edge.

Recently, I was a part-time researcher in the Advanced Technology Group at Dolby Labs in 2025, working on efficient fine-tuning of large foundation models. Previously, I was a Research Intern at Cisco Research for Summer 2024, where I worked on machine learning for distributed systems characterization.

I received my master's degree in Computer Science and my bachelor's degree in Computer Engineering, both from University of Illinois Urbana-Champaign, where I was advised by Prof. Sibin Mohan.

In the past, I spent two summers as a research intern in the Computational Research Division at Lawrence Berkeley National Laboratory. During my undergraduate studies, I spent two years as a part-time researcher at National Center for Supercomputing Applications.

Email: debopam [dot] sanyal [at] gatech [dot] edu
Office: KACB 3110

Resume  /  Google Scholar  /  Github  /  Twitter  /  LinkedIn

Publications

• DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation.
  Divyansh Srivastava, Akshay Mehra*, Pranav Maneriker*, Debopam Sanyal, Vishnu Raj, Vijay Kamarshi, Fan Du, Joshua Kimball.
  IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
  [Paper]


• LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data.
  Debopam Sanyal, Hongjie Chen, Alexey Tumanov, Joshua Kimball.
  Workshop on Machine Learning and Systems (EuroMLSys), ACM European Conference on Computer Systems (EuroSys), 2026.
  [Paper][Slides]


• KLAS: Using Similarity to Stitch Neural Networks for an Improved Accuracy-Efficiency Tradeoff.
  Debopam Sanyal, Anantharaman Iyer, Alind Khare, Trisha Jain, Akshay Jajoo, Myungjin Lee, Clayton Kerce, Alexey Tumanov.
  International Conference on Learning Representations (ICLR), 2026.
  [Paper][Slides]


• VillainNet: Targeted Poisoning Attacks Against SuperNets Along the Accuracy-Latency Pareto Frontier.
  David Oygenblik, Abhinav Vemulapalli, Animesh Agrawal, Debopam Sanyal, Alexey Tumanov, Brendan Saltaformaggio.
  ACM Conference on Computer and Communications Security (CCS), 2025.
  [Paper]


• Client Availability in Federated Learning: It Matters!
  Dhruv Garg*, Debopam Sanyal*, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska.
  Workshop on Machine Learning and Systems (EuroMLSys), ACM European Conference on Computer Systems (EuroSys), 2025.
  [Paper][Slides]


• Sci-Key: A Keyword Extraction Pipeline for Scientific Documents.
  Anna Giannakou, Oluwamayowa Amusat, Debopam Sanyal, Lavanya Ramakrishnan.
  Knowledge-Based Systems (KBS), 2024.
  [Paper]


• Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems.
  Debopam Sanyal, Jui-Tse Hung, Manav Agrawal, Prahlad Jasti, Shahab Nikkhoo, Somesh Jha, Tianhao Wang, Sibin Mohan, Alexey Tumanov.
  CoRR arXiv preprint, 2023.
  [Paper]


• Improving Schedule Indistinguishability in Real-Time Systems.
  Debopam Sanyal.
  Preprint, 2022.
  [Paper]


• Attacking Schedule Indistinguishability in Real-Time Systems.
  Debopam Sanyal.
  Master's Thesis, Department of Computer Science, University of Illinois Urbana-Champaign, 2022.
  [Paper]


• Indistinguishability Prevents Scheduler Side Channels in Real-Time Systems.
  Chien-Ying Chen, Debopam Sanyal, Sibin Mohan.
  ACM Conference on Computer and Communications Security (CCS), 2021.
  [Paper][Slides]


• Feature Selection Metrics: Similarities, Differences, and Characteristics of the Selected Models.
  Debopam Sanyal, Nigel Bosch, Luc Paquette.
  International Conference on Educational Data Mining (EDM), 2020.
  [Paper][Slides]


• Optimizing Networking Approaches using P4 Programming.
  Debopam Sanyal.
  Bachelor's Thesis, Department of Electrical & Computer Engineering, University of Illinois Urbana-Champaign, 2020.
  [Paper][Slides]