Publications | Dr. Murari Mandal

2025

OrgAccess: A Benchmark for Role Based Access Control in Organization Scale LLMs

Debdeep Sanyal , Umakanta Maharana , Yash Sinha , and 4 more authors

2025

source code PDF
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style

Debdeep Sanyal , Agniva Maiti , Umakanta Maharana , and 4 more authors

2025
Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Framework

Aakash Sen Sharma , Debdeep Sanyal , Priyansh Srivastava , and 4 more authors

2025

PDF
Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation

Soham Roy , Abhishek Mishra , Shirish Karande , and 1 more author

2025

source code PDF
Right Prediction, Wrong Reasoning: Uncovering LLM Misalignment in RA Disease Diagnosis

Umakanta Maharana , Sarthak Verma , Avarna Agarwal , and 4 more authors

2025

This paper discusses the implications of LLM misalignment in medical diagnostics.

source code PDF
ALU: Agentic LLM Unlearning

Debdeep Sanyal , and Murari Mandal

arXiv preprint arXiv:2502.00406, 2025

Abs PDF

Information removal or suppression in large language models (LLMs) is a desired functionality, useful in AI regulation, legal compliance, safety, and privacy. LLM unlearning methods aim to remove information on demand from LLMs. Current LLM unlearning methods struggle to balance the unlearning efficacy and utility due to the competing nature of these objectives. Keeping the unlearning process computationally feasible without assuming access to the model weights is an overlooked area. We present the first agentic LLM unlearning (\textttALU) method, a multi-agent, retrain-free, model-agnostic approach to LLM unlearning that achieves effective unlearning while preserving the utility. Our \textttALU framework unlearns by involving multiple LLM agents, each designed for a specific step in the unlearning process, without the need to update model weights for any of the agents in the framework. Users can easily request any set of unlearning instances in any sequence, and \textttALU seamlessly adapts in real time. This is facilitated without requiring any changes in the underlying LLM model. Through extensive experiments on established benchmarks (TOFU, WMDP, WPU) and jailbreaking techniques (many shot, target masking, other languages), we demonstrate that \textttALU consistently stands out as the most robust LLM unlearning framework among current state-of-the-art methods while incurring a low constant-time cost. We further highlight \textttALU’s superior performance compared to existing methods when evaluated at scale. Specifically, \textttALU is assessed on up to 1000 unlearning targets, exceeding the evaluation scope of all previously proposed LLM unlearning methods.
ReviewEval: An Evaluation Framework for AI-Generated Reviews

Chavvi Kirtani , Madhav Krishan Garg , Tejash Prasad , and 3 more authors

arXiv preprint arXiv:2502.11736, 2025

Abs PDF

The escalating volume of academic research, coupled with a shortage of qualified reviewers, necessitates innovative approaches to peer review. While large language model (LLMs) offer potential for automating this process, their current limitations include superficial critiques, hallucinations, and a lack of actionable insights. This research addresses these challenges by introducing a comprehensive evaluation framework for AI-generated reviews, that measures alignment with human evaluations, verifies factual accuracy, assesses analytical depth, and identifies actionable insights. We also propose a novel alignment mechanism that tailors LLM-generated reviews to the unique evaluation priorities of individual conferences and journals. To enhance the quality of these reviews, we introduce a self-refinement loop that iteratively optimizes the LLM’s review prompts. Our framework establishes standardized metrics for evaluating AI-based review systems, thereby bolstering the reliability of AI-generated reviews in academic research.
Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints

Yash Sinha , Murari Mandal , and Mohan Kankanhalli

2025

AAAI-2025 Core A* source code Abs PDF

Unlearning methods for recommender systems (RS) have emerged to address privacy issues and concerns about legal compliance. However, evolving user preferences and content licensing issues still remain unaddressed. This is particularly true in case of multi-modal recommender systems (MMRS), which aim to accommodate the growing influence of multi-modal information on user preferences. Previous unlearning methods for RS are inapplicable to MMRS due to incompatibility of multi-modal user-item behavior data graph with the matrix based representation of RS. Partitioning based methods degrade recommendation performance and incur significant overhead costs during aggregation. This paper introduces MMRecUN, a new framework for multi-modal recommendation unlearning, which, to the best of our knowledge, is the first attempt in this direction. Given the trained recommendation model and marked forget data, we devise Reverse Bayesian Personalized Ranking (BPR) objective to force the model to forget it. MMRecUN employs both reverse and forward BPR loss mechanisms to selectively attenuate the impact of interactions within the forget set while concurrently reinforcing the significance of interactions within the retain set. Our experiments demonstrate that MMRecUN outperforms baseline methods across various unlearning requests when evaluated on benchmark multi-modal recommender datasets. MMRecUN achieves recall performance improvements of up to \mathbf49.85% compared to the baseline methods. It is up to 1.3× faster than the \textscGold model, which is trained on retain data from scratch. MMRecUN offers advantages such as superior performance in removing target elements, preservation of performance for retained elements, and zero overhead costs in comparison to previous methods.
Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation

Yash Sinha , Murari Mandal , and Mohan Kankanhalli

2025

IEEE TNNLS Abs PDF

Graph unlearning has emerged as a pivotal method to delete information from a pre-trained graph neural network (GNN). One may delete nodes, a class of nodes, edges, or a class of edges. An unlearning method enables the GNN model to comply with data protection regulations (i.e., the right to be forgotten), adapt to evolving data distributions, and reduce the GPU-hours carbon footprint by avoiding repetitive retraining. Existing partitioning and aggregation-based methods have limitations due to their poor handling of local graph dependencies and additional overhead costs. More recently, GNNDelete offered a model-agnostic approach that alleviates some of these issues. Our work takes a novel approach to address these challenges in graph unlearning through knowledge distillation, as it distills to delete in GNN (D2DGN). It is a model-agnostic distillation framework where the complete graph knowledge is divided and marked for retention and deletion. It performs distillation with response-based soft targets and feature-based node embedding while minimizing KL divergence. The unlearned model effectively removes the influence of deleted graph elements while preserving knowledge about the retained graph elements. D2DGN surpasses the performance of existing methods when evaluated on various real-world graph datasets by up to 43.1% (AUC) in edge and node unlearning tasks. Other notable advantages include better efficiency, better performance in removing target elements, preservation of performance for the retained elements, and zero overhead costs. Notably, our D2DGN surpasses the state-of-the-art GNNDelete in AUC by 2.4%, improves membership inference ratio by +1.3, requires 10.2×106 fewer FLOPs per forward pass and up to 3.2× faster.

2024

ConDa: Fast Federated Unlearning with Contribution Dampening

Vikram S Chundawat , Pushkar Niroula , Prasanna Dhungana , and 3 more authors

ArXiv, 2024

Abs PDF

Federated learning (FL) has enabled collaborative model training across decentralized data sources or clients. While adding new participants to a shared model does not pose great technical hurdles, the removal of a participant and their related information contained in the shared model remains a challenge. To address this problem, federated unlearning has emerged as a critical research direction, seeking to remove information from globally trained models without harming the model performance on the remaining data. Most modern federated unlearning methods use costly approaches such as the use of remaining clients data to retrain the global model or methods that would require heavy computation on client or server side. We introduce Contribution Dampening (ConDa), a framework that performs efficient unlearning by tracking down the parameters which affect the global model for each client and performs synaptic dampening on the parameters of the global model that have privacy infringing contributions from the forgetting client. Our technique does not require clients data or any kind of retraining and it does not put any computational overhead on either the client or server side. We perform experiments on multiple datasets and demonstrate that ConDa is effective to forget a client’s data. In experiments conducted on the MNIST, CIFAR10, and CIFAR100 datasets, ConDa proves to be the fastest federated unlearning method, outperforming the nearest state of the art approach by at least 100x. Our emphasis is on the non-IID Federated Learning setting, which presents the greatest challenge for unlearning. Additionally, we validate ConDa’s robustness through backdoor and membership inference attacks. We envision this work as a crucial component for FL in adhering to legal and ethical requirements.
UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

Yash Sinha , Murari Mandal , and Mohan S. Kankanhalli

In , 2024

Abs PDF

The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentially be achieved through anti-data samples (or anti-samples), unlearning method, and reversed loss function. While prior research has explored unlearning methods and reversed loss functions, the potential of anti-samples remains largely untapped. In this paper, we introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs). Our contributions are threefold; first, we propose a novel concept of anti-sample-induced unlearning; second, we generate anti-samples by leveraging misleading rationales, which help reverse learned associations and accelerate the unlearning process; and third, we enable fine-grained targeted unlearning, allowing for the selective removal of specific associations without impacting related knowledge - something not achievable by previous works. Results demonstrate that anti-samples offer an efficient, targeted unlearning strategy for LLMs, opening new avenues for privacy-preserving machine learning and model modification.
EcoVal: An Efficient Data Valuation Framework for Machine Learning

Ayush K Tarun , Vikram S Chundawat , Murari Mandal , and 3 more authors

2024

KDD-2024 Core A* source code Abs PDF

Quantifying the value of data within a machine learning workflow can play a pivotal role in making more strategic decisions in machine learning initiatives. The existing Shapley value based frameworks for data valuation in machine learning are computationally expensive as they require considerable amount of repeated training of the model to obtain the Shapley value. In this paper, we introduce an efficient data valuation framework EcoVal, to estimate the value of data for machine learning models in a fast and practical manner. Instead of directly working with individual data sample, we determine the value of a cluster of similar data points. This value is further propagated amongst all the member cluster points. We show that the overall data value can be determined by estimating the intrinsic and extrinsic value of each data. This is enabled by formulating the performance of a model as a \textitproduction function, a concept which is popularly used to estimate the amount of output based on factors like labor and capital in a traditional free economic market. We provide a formal proof of our valuation technique and elucidate the principles and mechanisms that enable its accelerated performance. We demonstrate the real-world applicability of our method by showcasing its effectiveness for both in-distribution and out-of-sample data. This work addresses one of the core challenges of efficient data valuation at scale in machine learning models.
Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models

Aakash Sen Sharma , Niladri Sarkar , Vikram Chundawat , and 2 more authors

2024

PDF
A Unified Framework for Continual Learning and Machine Unlearning

Romit Chatterjee , Vikram Chundawat , Ayush Tarun , and 2 more authors

2024

PDF

2023

Fast yet effective machine unlearning

Ayush K Tarun , Vikram S Chundawat , Murari Mandal , and 1 more author

IEEE Transactions on Neural Networks and Learning Systems, 2023

IEEE TNNLS source code PDF
Zero-Shot Machine Unlearning

Vikram S. Chundawat , Ayush K. Tarun , Murari Mandal , and 1 more author

IEEE Transactions on Information Forensics and Security, 2023

IEEE TIFS source code PDF
Deep Regression Unlearning

Ayush Kumar Tarun , Vikram Singh Chundawat , Murari Mandal , and 1 more author

In Proceedings of the 40th International Conference on Machine Learning , 23–29 jul 2023

ICML-2023 Core A* source code Abs PDF

With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand from a machine learning (ML) model. In the last few years, there have been notable developments in machine unlearning to remove the information of certain training data efficiently and effectively from ML models. In this work, we explore unlearning for the regression problem, particularly in deep learning models. Unlearning in classification and simple linear regression has been considerably investigated. However, unlearning in deep regression models largely remains an untouched problem till now. In this work, we introduce deep regression unlearning methods that generalize well and are robust to privacy attacks. We propose the Blindspot unlearning method which uses a novel weight optimization process. A randomly initialized model, partially exposed to the retain samples and a copy of the original model are used together to selectively imprint knowledge about the data that we wish to keep and scrub off the information of the data we wish to forget. We also propose a Gaussian fine tuning method for regression unlearning. The existing unlearning metrics for classification are not directly applicable to regression unlearning. Therefore, we adapt these metrics for the regression setting. We conduct regression unlearning experiments for computer vision, natural language processing and forecasting applications. Our methods show excellent performance for all these datasets across all the metrics. Source code: https://github.com/ayu987/deep-regression-unlearning
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks Using an Incompetent Teacher

Vikram S Chundawat , Ayush K Tarun , Murari Mandal , and 1 more author

Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2023

AAAI-2023 Core A* source code
A universal metric for robust evaluation of synthetic tabular data

Vikram S Chundawat , Ayush K Tarun , Murari Mandal , and 2 more authors

IEEE Transactions on Artificial Intelligence, Jun 2023

IEEE-TAI source code

2022

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

Murari Mandal , and Santosh Kumar Vipparthi

IEEE Transactions on Intelligent Transportation Systems, Jun 2022

PDF
Scene Independency Matters: An Empirical Study of Scene Dependent and Scene Independent Evaluation for CNN-Based Change Detection

Murari Mandal , and Santosh Kumar Vipparthi

IEEE Transactions on Intelligent Transportation Systems, Jun 2022

PDF

2021

AgriSegNet: Deep Aerial Semantic Segmentation Framework for IoT-Assisted Precision Agriculture

Tanmay Anand , Soumendu Sinha , Murari Mandal , and 2 more authors

IEEE Sensors Journal, Jun 2021

PDF
ReViewNet: A Fast and Resource Optimized Network for Enabling Safe Autonomous Driving in Hazy Weather Conditions

Aryan Mehra , Murari Mandal , Pratik Narang , and 1 more author

IEEE Transactions on Intelligent Transportation Systems, Jun 2021

PDF
3DCD: Scene Independent End-to-End Spatiotemporal Feature Learning Framework for Change Detection in Unseen Videos

Murari Mandal , Vansh Dhar , Abhishek Mishra , and 2 more authors

IEEE Transactions on Image Processing, Jun 2021

PDF
Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing

Aditya Mehta , Harsh Sinha , Murari Mandal , and 1 more author

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , Jan 2021

Core A PDF

2020

NTIRE 2020 Challenge on NonHomogeneous Dehazing

Codruta O. Ancuti , Cosmin Ancuti , Florin-Alexandru Vasluianu , and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , Jun 2020

PDF
AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data

Murari Mandal , Manal Shah , Prashant Meena , and 2 more authors

IEEE Geoscience and Remote Sensing Letters, Jun 2020

PDF
HIDeGan: A Hyperspectral-Guided Image Dehazing GAN

Aditya Mehta , Harsh Sinha , Pratik Narang , and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , Jun 2020

PDF
MotionRec: A Unified Deep Framework for Moving Object Recognition

Murari Mandal , Lav Kush Kumar , Mahipal Singh Saran , and 1 more author

In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , Mar 2020

Core A PDF
MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videos

Murari Mandal , Lav Kush Kumar , and Santosh Kumar Vipparthi

In Proceedings of the 28th ACM International Conference on Multimedia , Mar 2020

ACM MM Core A* Abs PDF

Visual data collected from Unmanned Aerial Vehicles (UAVs) has opened a new frontier of computer vision that requires automated analysis of aerial images/videos. However, the existing UAV datasets primarily focus on object detection. An object detector does not differentiate between the moving and non-moving objects. Given a real-time UAV video stream, how can we both localize and classify the moving objects, i.e. perform moving object recognition (MOR) The MOR is one of the essential tasks to support various UAV vision-based applications including aerial surveillance, search and rescue, event recognition, urban and rural scene understanding.To the best of our knowledge, no labeled dataset is available for MOR evaluation in UAV videos. Therefore, in this paper, we introduce MOR-UAV, a large-scale video dataset for MOR in aerial videos. We achieve this by labeling axis-aligned bounding boxes for moving objects which requires less computational resources than producing pixel-level estimates. We annotate 89,783 moving object instances collected from 30 UAV videos, consisting of 10,948 frames in various scenarios such as weather conditions, occlusion, changing flying altitude and multiple camera views. We assigned the labels for two categories of vehicles (car and heavy vehicle). Furthermore, we propose a deep unified framework MOR-UAVNet for MOR in UAV videos. Since, this is a first attempt for MOR in UAV videos, we present 16 baseline results based on the proposed framework over the MOR-UAV dataset through quantitative and qualitative experiments. We also analyze the motion-salient regions in the network through multiple layer visualizations. The MOR-UAVNet works online at inference as it requires only few past frames. Moreover, it doesn’t require predefined target initialization from user. Experiments also demonstrate that the MOR-UAV dataset is quite challenging.

2019

SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes

Murari Mandal , Manal Shah , Prashant Meena , and 1 more author

In 2019 IEEE International Conference on Image Processing (ICIP) , Mar 2019

PDF
3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

Murari Mandal , Vansh Dhar , Abhishek Mishra , and 1 more author

IEEE Signal Processing Letters, Mar 2019

PDF
Challenges in Time-Stamp Aware Anomaly Detection in Traffic Videos

Kuldeep Marotirao Biradar , Ayushi Gupta , Murari Mandal , and 1 more author

CoRR, Mar 2019

PDF