Trying to learn about deep learning faster than deep learning can learn about me.
EDUCATION
PhD student in CSE at IIT Kharagpur.
RESEARCH INTERESTS
Machine Learning, Deep Learning, Computer Vision, Image Processing
6
Scopus Publications
135
Scholar Citations
5
Scholar h-index
2
Scholar i10-index
Scopus Publications
Sample Efficient Demonstration Selection for In-Context Learning Proceedings of Machine Learning Research, 2025
A Data-Driven Defense Against Edge-Case Model Poisoning Attacks on Federated Learning Kiran Purohit, Soumi Das, Sourangshu Bhattacharya, Santu Rana Frontiers in Artificial Intelligence and Applications, 2024 Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing defenses, leading to a high attack success rate. We propose an effective defense using an external defense dataset, which provides information about the attack target. The defense dataset contains a mix of poisoned and clean examples, with only a few known to be clean. The proposed method, DataDefense, uses this dataset to learn a poisoned data detector model which marks each example in the defense dataset as poisoned or clean. It also learns a client importance model that estimates the probability of a client update being malicious. The global model is then updated as a weighted average of the client models’ updates. The poisoned data detector and the client importance model parameters are updated using an alternating minimization strategy over the Federated Learning rounds. Extensive experiments on standard attack scenarios demonstrate that DataDefense can defend against model poisoning attacks where other state-of-the-art defenses fail. In particular, DataDefense is able to reduce the attack success rate by at least ∼ 40% on standard attack setups and by more than 80% on some setups. Furthermore, DataDefense requires very few defense examples (as few as five) to achieve a near-optimal reduction in attack success rate.
A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs Transactions on Machine Learning Research, 2024
EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning Kiran Purohit, Venktesh V, Raghuram Devalla, Krishna Mohan Yerragorla, Sourangshu Bhattacharya, Avishek Anand Emnlp 2024 2024 Conference on Empirical Methods in Natural Language Processing Proceedings of the Conference, 2024 Kiran Purohit, Venktesh V, Raghuram Devalla, Krishna Mohan Yerragorla, Sourangshu Bhattacharya, Avishek Anand. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
Accurate and Efficient Channel pruning via Orthogonal Matching Pursuit Kiran Purohit, Anurag Parvathgari, Soumi Das, Sourangshu Bhattacharya ACM International Conference Proceeding Series, 2022 The deeper and wider architectures of recent convolutional neural networks (CNN) are responsible for superior performance in computer vision tasks. However, they also come with an enormous model size and heavy computational cost. Filter pruning (FP) is one of the methods applied to CNNs for compression and acceleration. Various techniques have been recently proposed for filter pruning. We address the limitation of the existing state-of-the-art method and motivate our setup. We develop a novel method for filter selection using sparse approximation of filter weights. We propose an orthogonal matching pursuit (OMP) based algorithm for filter pruning (called FP-OMP). We also propose FP-OMP Search, which address the problem of removal of uniform number of filters from all the layers of a network. FP-OMP Search performs a search over all the layers with a given batch size of filter removal. We evaluate both FP-OMP and FP-OMP Search on benchmark datasets using standard ResNet architectures. Experimental results indicate that FP-OMP Search consistently outperforms the baseline method (LRF) by nearly . We demonstrate both empirically and visually, that FP-OMP Search prunes different number of filters from different layers. Further, timing profile experiments show that FP-OMP improves over the running time of LRF.
Measuring the Degree of Suitability of Edge Detection Operators Prior to an Application Abhishek Kesarwani, Kiran Purohit, Mamata Dalui, Dakshina Ranjan Kisku Proceedings of 2020 IEEE Applied Signal Processing Conference Aspcon 2020, 2020 Unlike image restoration, image enhancement techniques are found to be subjective in nature as the appearance of an output image depends upon human perception. Hence, it is very difficult to determine the appropriateness of image enhancement techniques including edge detection operators prior to an application. This paper makes use of regression models to determine the suitability of edge detection operators before operators to be executed. With the existing operators, a novel Hybrid technique is used in the evaluation. The Hybrid detector is designed by combining Canny and Sobel operators with the gradient of texton image. This approach estimates a model as an objective function to determine the degree of proximity or suitability of edge detection operators under regression constraints on two publicly available databases, viz. the BSDS300 and the Multi-cue. The experimental results exhibit that the Hybrid edge detector outperforms other operators for measuring the proximity for appropriateness.
RECENT SCHOLAR PUBLICATIONS
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning K Purohit, R Narayanam, S Pal Association for Computational Linguistics (ACL) , 2026 2026
Sample Efficient Demonstration Selection for In-Context Learning K Purohit, V Venktesh, S Bhattacharya, A Anand International Conference on Machine Learning (ICML) , 2025 2025 Citations: 9
EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning K Purohit, V Venktesh, R Devalla, KM Yerragorla, S Bhattacharya, ... Empirical Methods in Natural Language Processing (EMNLP) , 2024 2024 Citations: 7
A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs K Purohit, AR Parvathgari, S Bhattacharya Transactions on Machine Learning Research (TMLR) , 2024 2024 Citations: 2
A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning K Purohit, S Das, S Bhattacharya, S Rana 27th European Conference on Artificial Intelligence (ECAI) , 2024 2024 Citations: 11
Accurate and Efficient Channel pruning via Orthogonal Matching Pursuit K Purohit, A Parvathgari, S Das, S Bhattacharya Proceedings of the Second International Conference on AI-ML Systems, 1-8 , 2022 2022 Citations: 4
Covid-19 detection on chest x-ray and ct scan images using multi-image augmented deep learning model K Purohit, A Kesarwani, D Ranjan Kisku, M Dalui International Conference on Mathematics and Computing (ICMC), 395-413 , 2022 2022 Citations: 96
Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation K Purohit, O Iqbal, A Mullick arXiv preprint arXiv:2105.11412 , 2021 2021
Measuring the Degree of Suitability of Edge Detection Operators Prior to an Application A Kesarwani, K Purohit, M Dalui, DR Kisku 2020 IEEE Applied Signal Processing Conference (ASPCON), 128-133 , 2020 2020 Citations: 6
MOST CITED SCHOLAR PUBLICATIONS
Covid-19 detection on chest x-ray and ct scan images using multi-image augmented deep learning model K Purohit, A Kesarwani, D Ranjan Kisku, M Dalui International Conference on Mathematics and Computing (ICMC), 395-413 , 2022 2022 Citations: 96
A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning K Purohit, S Das, S Bhattacharya, S Rana 27th European Conference on Artificial Intelligence (ECAI) , 2024 2024 Citations: 11
Sample Efficient Demonstration Selection for In-Context Learning K Purohit, V Venktesh, S Bhattacharya, A Anand International Conference on Machine Learning (ICML) , 2025 2025 Citations: 9
EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning K Purohit, V Venktesh, R Devalla, KM Yerragorla, S Bhattacharya, ... Empirical Methods in Natural Language Processing (EMNLP) , 2024 2024 Citations: 7
Measuring the Degree of Suitability of Edge Detection Operators Prior to an Application A Kesarwani, K Purohit, M Dalui, DR Kisku 2020 IEEE Applied Signal Processing Conference (ASPCON), 128-133 , 2020 2020 Citations: 6
Accurate and Efficient Channel pruning via Orthogonal Matching Pursuit K Purohit, A Parvathgari, S Das, S Bhattacharya Proceedings of the Second International Conference on AI-ML Systems, 1-8 , 2022 2022 Citations: 4
A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs K Purohit, AR Parvathgari, S Bhattacharya Transactions on Machine Learning Research (TMLR) , 2024 2024 Citations: 2
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning K Purohit, R Narayanam, S Pal Association for Computational Linguistics (ACL) , 2026 2026
Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation K Purohit, O Iqbal, A Mullick arXiv preprint arXiv:2105.11412 , 2021 2021
