This paper investigates a network side-channel vulnerability in multi-tenant datacenter fabrics caused by shared congestion behavior, achieving up to 97.3% run-level accuracy in workload inference.

Proposed ProFlow, a proactive flow-placement framework using distributed telemetry signals and offline-trained RL for identifying precursor congestion conditions and rerouting protected flows in multi…

This paper proposes a host-driven method for flowlet balancing using Segment Routing over IPv6 (SRv6), reducing tail latency by 15% and 33% compared to random flowlet balancing and ECMP, respectively.

The paper proposes n-VM, a novel Layer-1 architecture that unifies multiple heterogeneous virtual machines (VMs) onto a shared consensus and state layer, solving cross-chain fragmentation issues.

This paper proposes CAPS, a scheduling layer for data centers that separates rate computation and packet scheduling, reducing queue occupancy by up to 10x without throughput loss.

This paper proposes cross-IP request coalescing to reduce latency in virtualized cloud data centers by submitting multi-device I/O as a single compound request.

The ZCube topology, which eliminates path multiplicity and reduces switching hardware, delivers better performance for large model training and inference than traditional multipath datacenter networks…

The paper introduces Spandana, an architecture that decouples SLO enforcement from cost optimization in cloud-based online services, achieving high utilization, strict SLO adherence, and cost savings.

This paper introduces Virtual Time-Sensitive Networking (V-TSN), a software-defined overlay for gPTP-based synchronization and TSN traffic shaping over general-purpose networks without specialized har…

The paper proposes a federated, high-throughput stream-processing framework for cross-sector threat detection and automated containment, achieving end-to-end operational convergence within 12-20 secon…

The paper proposes a method to improve the performance of fine-grained offloads on servers by overlapping the offload with other requests using server-side routing.

The paper introduces an open-source security framework that significantly improves cloud infrastructure security assessment by unifying identity and resource data, reducing false positives, and automa…

JoyNexus is a multi-tenant service for VLA model supervised fine-tuning, reinforcement learning, and evaluation, which decouples services, introduces group batching, and improves training efficiency.

This paper proposes a proactive fair scheduling framework to prevent fabric oversubscription and eliminate incast in Mixture of Experts (MoE) architectures, demonstrating consistent link utilization a…

The I/O Resource Manager (IORM) is presented as a multi-stage distributed scheduler to maintain consistent performance and enforce global I/O limits in shared-nothing disaggregated storage clusters.

This paper argues that idle cores on contemporary multicore processors can return compute capacity and proposes a budget-centric view of service core systems.