collaborators

5 papers

cs.LG2026

Graph Reconstruction from Differentially Private GNN Explanations

Rishi Raj Sahoo, Jyotirmaya Shivottam, Subhankar Mishra

Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Diffe…

cs.LG2026

GRAFT: Auditing Graph Neural Networks via Global Feature Attribution

Rishi Raj Sahoo, Subhankar Mishra

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive thei…

cs.CV2025

iWatchRoadv2: Pothole Detection, Geospatial Mapping, and Intelligent Road Governance

Rishi Raj Sahoo, Surbhi Saswati Mohanty, Subhankar Mishra

Road potholes pose significant safety hazards and maintenance challenges, particularly on India's diverse and under-maintained road networks. This paper presents iWatchRoadv2, a fu…

cs.CV2025

iWatchRoad: Scalable Detection and Geospatial Visualization of Potholes for Smart Cities

Rishi Raj Sahoo, Surbhi Saswati Mohanty, Subhankar Mishra

Potholes on the roads are a serious hazard and maintenance burden. This poses a significant threat to road safety and vehicle longevity, especially on the diverse and under-maintai…

cs.LG2025

ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labels

Rishi Raj Sahoo, Rucha Bhalchandra Joshi, Subhankar Mishra

Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal…