Publications

The principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model in a data-constrained setting, where the whole training dataset is inaccessible.

The principal aim of our work is to analyze such regret-tail behavior of optimal bandit algorithms in a relatively broader setting: policies that are optimized for generic families of reward distributions under significantly weaker structural assumptions

The principal objective of this work is to propose a hypothesis testing framework for estimating the influence of training data for a model prediction.

A hypothesis-testing definition of influence that explicitly captures training-time randomness, enabling consistent estimation of the influence of training data in a single training run.

The primary aim of this study is to propose a mathematical definition of forgetting in ML models and develop methodologies for forgetting specific undesired concepts from pre-trained classification models.

The principal aim of this study is to formulate a methodology tailored for the purposeful elimination of information linked to a specific class of data from a pre-trained classification network.

The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems.

The objective of this work is to prevent the generation of outputs containing undesired features from a pre-trained GAN where the underlying training data set is inaccessible.

The principal objective of this work is to propose a machine unlearning methodology that can prevent the generation of outputs containing undesired features from a pre-trained diffusion model.

The objective of this project is to utilize a LASER INDUCED BREAKDOWN SPECTROGRAPHY (LIBS) instrument for soil mineral composition analysis in agriculture, facilitated by an Android-controlled platform.