5 papers · 1 filter
f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
Subhodip Panda, Dhruv Tarsadiya, Shashwat Sourav +2
Influence estimation methods promise to explain and debug machine learning by estimating the impact of individual samples on the final model. Yet, existing methods collapse under t…
Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach
Subhodip Panda, Varun M S, Shreyans Jain +2
For a responsible and safe deployment of diffusion models in various domains, regulating the generated outputs from these models is desirable because such models could generate und…
Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks
Piyush Tiwary, Atri Guha, Subhodip Panda +1
Owing to the growing concerns about privacy and regulatory compliance, it is desirable to regulate the output of generative models. To that end, the objective of this work is to pr…
FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative Models
Subhodip Panda, Prathosh AP
The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores t…
Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective
Subhodip Panda, Shashwat Sourav, Prathosh A. P
In order to adhere to regulatory standards governing individual data privacy and safety, machine learning models must systematically eliminate information derived from specific sub…