Summary
Siladittya Manna is a Research Associate with nine years of experience advancing self-supervised and federated learning methods, particularly for medical image analysis and signature verification. Currently at IISc Bengaluru, he focuses on federated learning for vision-language models, gradient inversion attacks, and source-free domain adaptation, building on prior work improving aggregation and representation learning in cross-device settings. His PhD from ISI Kolkata underpins a rigorous approach to SSL, and he has held research roles at HKBU and ISI where he explored incremental learning and interest-point feature clustering. Beyond core ML, he is interested in meta-learning, LLMs/VLMs, and the vulnerability surface of PEFT frameworks—an emerging practical concern he investigates. Colleagues describe him as researcher-engineer hybrid who translates theoretical insights into applied defenses and adaptation strategies for real-world medical and vision tasks.
9 years of coding experience
1 year of employment as a software developer
Dual Degree(B.Tech-M.Tech) Electronics and Telecommunications Engineering (B.Tech) + Microelectronics and VLSI (M.Tech), Dual Degree(B.Tech-M.Tech) Electronics and Telecommunications Engineering (B.Tech) + Microelectronics and VLSI (M.Tech) at Indian Institute of Engineering Science and Technology (IIEST), Shibpur
10+2 Science, 10+2 Science at Chandernagore Sri Aurobindo Vidyamandir
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Indian Statistical Institute, Kolkata
English, Hindi, Bengali