works on

From the 2 of 10 linked papers with an AI index.

collaborators

10 papers

cs.NI2026

Round Trip Time: A Benign Signal or an Indirect Window into Datacenter Workloads?

Sourya Saha, Md Nurul Absur, Saptarshi Debroy

The paper studies how round‑trip time (RTT) variations in shared multi‑tenant datacenter networks can be used as a side‑channel to infer co‑located workloads, showing high inferenc…

cs.NI2026

ProFlow: RL-Driven and Performance-Aware Proactive Flow Placement in Datacenter Networks

Sourya Saha, Md Nurul Absur, Saptarshi Debroy

ProFlow is a system that uses telemetry data and reinforcement learning to detect early signs of congestion in datacenter networks and proactively reroute important traffic before…

cs.CR2026

Variational Autoencoder-Based Black-Box Adversarial Attack on Collaborative DNN Inference

Shima Yousefi, Motahare Mounesan, Saptarshi Debroy

In recent years, Deep Neural Networks (DNNs) have become increasingly integral to IoT-based environments, enabling realtime visual computing. However, the limited computational cap…

cs.CV2026

Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference

Shima Yousefi, Saptarshi Debroy

Collaborative inference of object classification Deep neural Networks (DNNs) where resource-constrained end-devices offload partially processed data to remote edge servers to compl…

cs.CV2026

Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelines

Sourya Saha, Saptarshi Debroy

Immersive extended reality (XR) applications introduce latency-critical workloads that must satisfy stringent real-time responsiveness while operating on energy- and battery-constr…

cs.LG2025

Reinforcement Learning-Driven Edge Management for Reliable Multi-view 3D Reconstruction

Motahare Mounesan, Sourya Saha, Houchao Gan +2

Real-time multi-view 3D reconstruction is a mission-critical application for key edge-native use cases, such as fire rescue, where timely and accurate 3D scene modeling enables sit…