From the 2 of 8 linked papers with an AI index.
8 papers
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…
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…
Understanding Sensor Vulnerabilities in Industrial XR Tracking
Sourya Saha, Md. Nurul Absur
Extended Reality (XR) systems deployed in industrial and operational settings rely on Visual--Inertial Odometry (VIO) for continuous six-degree-of-freedom pose tracking, yet these…
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…
Detection of Misreporting Attacks on Software-Defined Immersive Environments
Sourya Saha, Md Nurul Absur, Shima Yousefi +1
The ability to centrally control network infrastructure using a programmable middleware has made Software-Defined Networking (SDN) ideal for emerging applications, such as immersiv…
Detection and Recovery of Adversarial Slow-Pose Drift in Offloaded Visual-Inertial Odometry
Soruya Saha, Md Nurul Absur, Saptarshi Debroy
Visual-Inertial Odometry (VIO) supports immersive Virtual Reality (VR) by fusing camera and Inertial Measurement Unit (IMU) data for real-time pose. However, current trend of offlo…