Sasikanth Kotti

I am currently pursuing my Ph.D at IAB lab from IITJ-Indian Institute of Technology Jodhpur in part-time mode under the guidance of Dr. Mayank Vatsa and Dr. Richa Singh.

I recently completed Master's in Artificial Intelligence (M.Tech) at IITJ-Indian Institute of Technology Jodhpur. I was advised by Dr. Mayank Vatsa and Dr. Richa Singh for my Master's Thesis on "Bias and Fairness in Low Resolution(Very) Image Recognition" at IAB lab.

I was the recepient of Silver Medal and Mrs. Chander Mohini & Mr. Jeewan Kapoor Merit Prize for the best academic performance in the graduating class of 2023 of M.Tech. (Artificial Intelligence) Program at IIT Jodhpur

My current research interests span Computer Vision, Trusted AI, Machine Learning and Deep learning areas.

I'm also a Volunteer Research Engineer at  OpenMined where I contribute to Privacy-Preserving technologies in Computer Vision Domain.

I am also an active participant at ML Collective, Cohere For AI, Trustworthy ML and AI Vulnerability Database communities

Email  /  GitHub  /  Google Scholar  /  Twitter  /  LinkedIn  /  Blog

profile photo

News

Master's Thesis

project image

Bias and Fairness in Low Resolution Image Recognition


IIT Jodhpur - Masters Thesis
report / presentation / code /

Publications

project image

On Biased Behavior of GANs for Face Verification


Sasikanth Kotti*, Mayank Vatsa, Richa Singh
Responsbile Computer Vision workshop, ECCV 2022.
arxiv / video / poster

project image

When Differential Privacy Meets Interpretability: A Case Study


Rakshit Naidu, Aman Priyanshu, Aadith Kumar, Sasikanth Kotti*, Haofan Wang, Fatemehsadat Mireshghallah
Extended abstract at Responsible Computer Vision (RCV) workshop, CVPR 2021. Privacy-Preserving Machine Learning (PPML) workshop, CCS 2021.
arxiv / poster

project image

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?


Archit Uniyal, Rakshit Naidu, Sasikanth Kotti*, Sahib Singh, Patrik Joslin Kenfack, Fatemehsadat Mireshghallah, Andrew Trask
Machine Learning for Data (ML4DATA) workshop, ICML 2021. Privacy-Preserving Machine Learning (PPML) workshop, CCS 2021.
arxiv / code / poster

project image

Benchmarking Differentially Private Residual Networks for Medical Imagery


Sahib Singh, Harshvardhan Sikka, Sasikanth Kotti*, Andrew Trask
International Conference on Machine Learning (2020) Workshop - Healthcare Systems (HSYS) workshop, ICML 2020.
arxiv / code / poster




Selected Projects

These include coursework, side projects and unpublished research work.

project image

Database Tuning with NLP


IIT Jodhpur CSL7090: Software and Data Engineering
2022-04-18
presentation / code /

project image

Have we met before: ID'ing face


IIT Jodhpur CSL7530: Advanced Machine Learning
2021-12-01
report / presentation /

project image

FairMIA: The heuristic based Fair Influence Maximization


IIT Jodhpur CSL7390: Social Network Analysis
2021-11-15
report / presentation / code /

project image

Efface the Haze


IIT Jodhpur CSL7360: Computer Vision
2021-06-12
report / presentation / code /

project image

Machine Translation


IIT Jodhpur CSL7340: Natural Language Processing
2021-06-09
report / presentation /




Professional Services

  • Reviewer for Tiny Papers 2023, 2024, a DEI initiative at ICLR
  • Reviewer for Machine Learning for Health (ML4H) 2023 Symposium
  • Reviewer for NeurIPS 2023 Workshop - XAI in Action: Past, Present, and Future Applications

  • Design and source code from Leonid Keselman's website