We introduce ImageNet-LC, a benchmark for evaluating object-centric robustness of vision models under localized corruptions.
@inproceedings{swain2026imagenet,title={{ImageNet-LC}: A Benchmark for Object-Centric Robustness under Localized Corruptions},author={Swain, Subrat Kumar and Gupta, Siddharth and others},booktitle={International Conference on Pattern Recognition (ICPR)},year={2026},note={[CORE B]}}
EuroS&P-W
G2AP: Gradient-Guided Adversarial Perturbation in Network Security
Subrat Kumar Swain, Vishal Maurya, Dan D. Kim, and 1 more author
In IEEE European Symposium on Security and Privacy Workshops (EuroS&P-W), 2026
We propose G2AP, a gradient-guided adversarial perturbation framework for attacking network security systems.
@inproceedings{swain2026g2ap,title={{G2AP}: Gradient-Guided Adversarial Perturbation in Network Security},author={Swain, Subrat Kumar and Maurya, Vishal and Kim, Dan D. and Kumar, Vireshwar},booktitle={IEEE European Symposium on Security and Privacy Workshops (EuroS\&P-W)},year={2026},note={[CORE A]}}
AsiaCCS
GhosTurb: Practical Adversarial Perturbation Framework for IoT Networks
GhosTurb is a practical adversarial perturbation framework targeting IoT network security.
@article{swain2026ghosturb,title={{GhosTurb}: Practical Adversarial Perturbation Framework for {IoT} Networks},author={Swain, Subrat Kumar and others},year={2026},note={Submitted to AsiaCCS 2026}}
2024
DSN
PANDA: Practical Adversarial Attack Against Network Intrusion Detection
Subrat Kumar Swain, Vireshwar Kumar, Guangdong Bai, and 1 more author
In International Conference on Dependable Systems and Networks (DSN), 2024
We present PANDA, a practical adversarial attack framework targeting network intrusion detection systems, demonstrating the real-world vulnerability of ML-based security systems.
@inproceedings{swain2024panda,title={{PANDA}: Practical Adversarial Attack Against Network Intrusion Detection},author={Swain, Subrat Kumar and Kumar, Vireshwar and Bai, Guangdong and Kim, Dan D.},booktitle={International Conference on Dependable Systems and Networks (DSN)},year={2024},note={[CORE A]}}
2023
ECAI
SPAT: Semantic-Preserving Adversarial Transformation for Perceptually Similar Adversarial Examples
Subrat Kumar Swain, Vireshwar Kumar, Dan D. Kim, and 1 more author
In European Conference on Artificial Intelligence (ECAI), 2023
We propose SPAT, a semantic-preserving adversarial transformation that generates perceptually similar adversarial examples while preserving the semantic content of the original input.
@inproceedings{swain2023spat,title={{SPAT}: Semantic-Preserving Adversarial Transformation for Perceptually Similar Adversarial Examples},author={Swain, Subrat Kumar and Kumar, Vireshwar and Kim, Dan D. and Bai, Guangdong},booktitle={European Conference on Artificial Intelligence (ECAI)},year={2023},note={[CORE A]}}
2020
Measurement
Deep Learning and Wavelet Transform Integrated Approach for Short-term Solar PV Power Prediction
M. Mishra, P. B. Dash, J. Nayak, and 1 more author
This paper presents an integrated approach using deep learning and wavelet transform for accurate short-term solar PV power prediction.
@article{mishra2020deep,title={Deep Learning and Wavelet Transform Integrated Approach for Short-term Solar {PV} Power Prediction},author={Mishra, M. and Dash, P. B. and Nayak, J. and Swain, Subrat Kumar},journal={Measurement},year={2020},publisher={Elsevier},note={[IF: 5.131]}}