The CLEVER Project is tackling one of the most critical questions in AI for distributed environments: how do we make machine learning resilient when data comes from a wide range of sources—with varying levels of trust?  📍 Presented at the Cloud Edge Continuum Workshop (CEC23), our latest research explores: 🔹 How trust scores—based on data provenance…

We’re excited to present a breakthrough from the CLEVER Project: a novel RDMA over InfiniBand Communicator that significantly accelerates GPGPU virtualization using GVirtuS — enabling smarter, faster, and more efficient AI workloads across remote GPUs ⚡🧠  🔍 Why this matters: Traditional TCP/IP-based GPU virtualization is plagued by context switches and latency. With the new RDMA Communicator,…

We’re thrilled to share our latest breakthrough from the CLEVER Project — showcased at #OFC2024! Our research introduces Data Processing Units (DPUs) with embedded GPUs as a game-changing solution for programmable, high-performance optical metro/edge networks. 🌍✨  These powerful DPUs, integrated with coherent pluggable transceivers, consolidate computing, networking, and optical functionalities in a single compact platform….

CLEVER integrates P4-based programmable switches and smart NICs (DPUs) to revolutionize network security within the cloud-edge continuum. By leveraging hardware-accelerated technologies, CLEVER tackles modern challenges like DDoS attack mitigation and vulnerability detection with unmatched efficiency.  Key Highlights 🔑  DDoS Detection & Mitigation: CLEVER employs cascaded Deep Neural Networks (DNNs) distilled into Lookup Tables (LUTs). This…

📣 We’re proud to share another major step forward in the CLEVER Project—our latest public deliverable is now available on Zenodo!  📘 What’s it about? This document presents concrete use case scenarios and initial Key Performance Indicators (KPIs) that guide the deployment of CLEVER’s AI-powered orchestration platform in real-world environments.  🏭 Our use cases focus on: …