SERB Startup Research Grant

SERB Funded Project [Jan 2024 - Present]

SERB Logo

Science and Engineering Research Board
(Statutory Body Established Through an Act of Parliament: SERB Act 2008)
Government of India

Project Details:

  • Project Title: Machine Unlearning for Selective Removal of Digital Data Footprint from Deep Learning Models
  • File Number: SRG/2023/001686
  • Principal Investigator (PI): Dr. Murari Mandal
  • Institute: Kalinga Institute of Industrial Technology (KIIT)
  • Project Start Date: 02-Jan-2024
  • Duration: 24 months
  • Project Completion Date: 01-Jan-2026
  • Total Budget: 30,50,300 INR
  • Status: Ongoing
  • Budget Released So Far: 23,30,000 INR
  • Research Fellow: Umakanta Maharana

Introduction

Welcome to our exploration of cutting-edge research in machine unlearning! Our project, supported by the Science and Engineering Research Board (SERB), aims to address one of the most pressing concerns in today’s digital age: the selective removal of digital data footprints from deep learning models.

Project Overview

In the rapidly evolving landscape of artificial intelligence, the ability to unlearn specific data points from a trained model is crucial. This capability is essential for complying with privacy regulations, such as the GDPR, and for ensuring that models do not perpetuate biases or inaccuracies associated with certain data.

Objectives

The primary goal of this project is to develop methodologies for effectively and efficiently removing specific data from deep learning models without compromising their overall performance. This involves:

  • Designing algorithms for selective data removal.
  • Ensuring the model’s robustness and accuracy post-unlearning.
  • Addressing the challenges of data integrity and consistency.

Current Progress

Since the project’s inception in January 2024, significant strides have been made:

  • Algorithm Development: Initial prototypes of unlearning algorithms have been tested with promising results.
  • Model Training: Deep learning models have been trained with diverse datasets to evaluate the effectiveness of the unlearning process.
  • Budget Utilization: Out of the total budget of 30,50,300 INR, 23,30,000 INR has been released and utilized effectively to support research activities.

Future Directions

As we move forward, our focus will be on refining these algorithms, conducting extensive testing, and ensuring their scalability and applicability in real-world scenarios. Collaboration with industry partners and continued support from SERB will be instrumental in achieving our objectives.

Published papers

Paper Title Paper Link Publication Details
EcoVal: An Efficient Data Valuation Framework for Machine Learning https://arxiv.org/pdf/2402.09288 KDD 2025
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints https://ojs.aaai.org/index.php/AAAI/article/view/33367/35522 AAAI 2025
Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation https://arxiv.org/pdf/2309.16173 IEEE TNNLS
UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs https://arxiv.org/pdf/2410.17050 TMLR
A Unified Framework for Continual Learning and Machine Unlearning https://arxiv.org/pdf/2408.11374v1 arXiv
Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models https://arxiv.org/pdf/2409.05668 arXiv
ALU: Agentic LLM Unlearning https://arxiv.org/pdf/2502.00406 arXiv

To further explore the concepts and advancements in machine unlearning, you can refer to the following related papers:

Conclusion

Our journey towards enabling machine unlearning is just beginning, and we are excited about the potential impact of this research. Stay tuned for more updates as we work towards making our digital world more secure and privacy-conscious.

Thank you for your interest and support!

For more information and updates on this project, feel free to reach out to me at KiiT. Let’s collaborate and innovate for a smarter, safer future!