Atul Sharma
Atul Sharma
Hi, I am a graduate student at Purdue University. I am a research assistant in the Dependable Computing Systems Lab (DCSL) supervised by Prof. Saurabh Bagchi in the School of Electrical and Computer Engineering, and in the Innovatory for Cells and Machines Lab (ICAN) supervised by Prof. Somali Chaterji in the ABE Department. Previously, I graduated with a B.Tech degree from the Indian Institute of Technology, Kharagpur (IIT KGP) with a major in E&ECE and a minor in CSE.
At Purdue, my work focuses on developing and enhancing collaborative machine learning algorithms, such as Federated Learning and Decentralized Learning, with an emphasis on addressing their vulnerabilities. My efforts are geared towards making these algorithms both more secure and more efficient.
sharm438[at]purdue[dot]edu
Publications
- [Article] Sharma, Atul, Joshua C. Zhao, Wei Chen, Qiang Qiu, Saurabh Bagchi, and Somali Chaterji. “How to Learn Collaboratively-Federated Learning to Peer-to-Peer Learning and What’s at Stake.” In 2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks-Supplemental Volume (DSN-S), pp. 122-126. IEEE, 2023.
- [Article] Zhao, Joshua C., Ahaan Dabholkar, Atul Sharma, and Saurabh Bagchi. “Leak and Learn: An Attacker’s Cookbook to Train Using Leaked Data from Federated Learning.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12247-12256. 2024.
- [Article] Zhao, Joshua C., Ahmed Roushdy Elkordy, Atul Sharma, Yahya H. Ezzeldin, Salman Avestimehr, and Saurabh Bagchi. “The resource problem of using linear layer leakage attack in federated learning.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3974-3983. 2023.
- [Article] Zhao, Joshua C., Atul Sharma, Ahmed Roushdy Elkordy, Yahya H. Ezzeldin, Salman Avestimehr, and Saurabh Bagchi. “Loki: Large-scale data reconstruction attack against federated learning through model manipulation.” In 2024 IEEE Symposium on Security and Privacy (SP), pp. 1287-1305. IEEE, 2024.
- [Article] [Github] Sharma, Atul, Wei Chen, Joshua Zhao, Qiang Qiu, Saurabh Bagchi, and Somali Chaterji. “Flair: Defense against model poisoning attack in federated learning.” In Proceedings of the 2023 ACM Asia Conference on Computer and Communications Security, pp. 553-566. 2023.
- [Article] [Github] Sharma, Atul, Pranjal Jain, Ashraf Mahgoub, Zihan Zhou, Kanak Mahadik, and Somali Chaterji. “Lerna: transformer architectures for configuring error correction tools for short-and long-read genome sequencing.” BMC bioinformatics 23, no. 1 (2022): 25.
- [Article] Mukhopadhyay, Anand Kumar, Atul Sharma, Indrajit Chakrabarti, Arindam Basu, and Mrigank Sharad. “Power-efficient spike sorting scheme using analog spiking neural network classifier.” ACM Journal on Emerging Technologies in Computing Systems (JETC) 17, no. 2 (2021): 1-29.