Search Results for author: Dario Rossi

Found 14 papers, 1 papers with code

Local Evaluation of Time Series Anomaly Detection Algorithms

1 code implementation27 Jun 2022 Alexis Huet, Jose Manuel Navarro, Dario Rossi

In recent years, specific evaluation metrics for time series anomaly detection algorithms have been developed to handle the limitations of the classical precision and recall.

Anomaly Detection Time Series Anomaly Detection

How Much is Enough? A Study on Diffusion Times in Score-based Generative Models

no code implementations10 Jun 2022 Giulio Franzese, Simone Rossi, Lixuan Yang, Alessandro Finamore, Dario Rossi, Maurizio Filippone, Pietro Michiardi

Score-based diffusion models are a class of generative models whose dynamics is described by stochastic differential equations that map noise into data.

Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks

no code implementations26 Apr 2022 Dario Rossi, Liang Zhang

The tremendous achievements of Artificial Intelligence (AI) in computer vision, natural language processing, games and robotics, has extended the reach of the AI hype to other fields: in telecommunication networks, the long term vision is to let AI fully manage, and autonomously drive, all aspects of network operation.

Autonomous Driving Natural Language Processing

Quality Monitoring and Assessment of Deployed Deep Learning Models for Network AIOps

no code implementations28 Feb 2022 Lixuan Yang, Dario Rossi

Artificial Intelligence (AI) has recently attracted a lot of attention, transitioning from research labs to a wide range of successful deployments in many fields, which is particularly true for Deep Learning (DL) techniques.


A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

no code implementations11 Feb 2022 Kevin Fauvel, Alessandro Finamore, Fuxing Chen, Dario Rossi

Traffic classification, i. e. the identification of the type of applications flowing in a network, is a strategic task for numerous activities (e. g., intrusion detection, routing).

Intrusion Detection Traffic Classification

Neural combinatorial optimization beyond the TSP: Existing architectures under-represent graph structure

no code implementations3 Jan 2022 Matteo Boffa, Zied Ben Houidi, Jonatan Krolikowski, Dario Rossi

Recent years have witnessed the promise that reinforcement learning, coupled with Graph Neural Network (GNN) architectures, could learn to solve hard combinatorial optimization problems: given raw input data and an evaluator to guide the process, the idea is to automatically learn a policy able to return feasible and high-quality outputs.

Combinatorial Optimization

Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching

no code implementations13 Dec 2021 Alessandro Finamore, James Roberts, Massimo Gallo, Dario Rossi

While Deep Learning (DL) technologies are a promising tool to solve networking problems that map to classification tasks, their computational complexity is still too high with respect to real-time traffic measurements requirements.


HURRA! Human readable router anomaly detection

no code implementations23 Jul 2021 Jose M. Navarro, Dario Rossi

This paper presents HURRA, a system that aims to reduce the time spent by human operators in the process of network troubleshooting.

Anomaly Detection

Thinkback: Task-SpecificOut-of-Distribution Detection

no code implementations13 Jul 2021 Lixuan Yang, Dario Rossi

The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments.

Out-of-Distribution Detection

A First Look at Class Incremental Learning in Deep Learning Mobile Traffic Classification

no code implementations9 Jul 2021 Giampaolo Bovenzi, Lixuan Yang, Alessandro Finamore, Giuseppe Aceto, Domenico Ciuonzo, Antonio Pescapè, Dario Rossi

The recent popularity growth of Deep Learning (DL) re-ignited the interest towards traffic classification, with several studies demonstrating the accuracy of DL-based classifiers to identify Internet applications' traffic.

class-incremental learning Incremental Learning +1

FENXI: Deep-learning Traffic Analytics at the Edge

no code implementations25 May 2021 Massimo Gallo, Alessandro Finamore, Gwendal Simon, Dario Rossi

The design of FENXI decouples forwarding operations and traffic analytics which operates at different granularities i. e., packet and flow levels.

Heterogeneous Data-Aware Federated Learning

no code implementations12 Nov 2020 Lixuan Yang, Cedric Beliard, Dario Rossi

Federated learning (FL) is an appealing concept to perform distributed training of Neural Networks (NN) while keeping data private.

Federated Learning Traffic Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.