148 citations · 328 across the 9 of their papers we have counts for
10 papers
SVD-Based Typicality Maps for Out-of-Distribution Detection in Vision Transformers
Aldo Sean Sartor, Leandro de Souza Rosa, Andriy Enttsel +2
We present a method for analyzing the internal representations of Vision Transformers (ViTs) exploiting the geometry of their learned parameters. Each affine layer's weight matrix…
A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods
Leandro de Souza Rosa, Lorenzo Capelli, Clara Nunes Barrancos +2
Despite the success of convolutional neural networks in image classification tasks and their general application in multi-modal models, their susceptibility to out-of-distribution…
On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
Lorenzo Capelli, Leandro de Souza Rosa, Maurizio De Tommasi +8
The increasing autonomy of spacecraft demands fault-detection systems that are both reliable and explainable. This work addresses eXplainable Artificial Intelligence for onboard Fa…
Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications
Lorenzo Capelli, Leandro de Souza Rosa, Gianluca Setti +2
The recent explosive growth in Deep Neural Networks applications raises concerns about the black-box usage of such models, with limited trasparency and trustworthiness in high-stak…
RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off
Andriy Enttsel, Alex Marchioni, Andrea Zanellini +3
Extensive monitoring systems generate data that is usually compressed for network transmission. This compressed data might then be processed in the cloud for tasks such as anomaly…
Goal-Oriented Joint Source-Channel Coding: Distortion-Classification-Power Trade-off
Andriy Enttsel, Weichen Wang, Mauro Mangia +2
Joint source-channel coding is a compelling paradigm when low-latency and low-complexity communication is required. This work proposes a theoretical framework that integrates class…
Anomaly Detection based on Compressed Data: an Information Theoretic Characterization
Alex Marchioni, Andriy Enttsel, Mauro Mangia +2
We analyze the effect of lossy compression in the processing of sensor signals that must be used to detect anomalous events in the system under observation. The intuitive relations…
On Known-Plaintext Attacks to a Compressed Sensing-based Encryption: A Quantitative Analysis
Valerio Cambareri, Mauro Mangia, Fabio Pareschi +2
Despite the linearity of its encoding, compressed sensing may be used to provide a limited form of data protection when random encoding matrices are used to produce sets of low-dim…
Low-complexity Multiclass Encryption by Compressed Sensing
Valerio Cambareri, Mauro Mangia, Fabio Pareschi +2
The idea that compressed sensing may be used to encrypt information from unauthorised receivers has already been envisioned, but never explored in depth since its security may seem…
Rakeness in the design of Analog-to-Information Conversion of Sparse and Localized Signals
Mauro Mangia, Riccardo Rovatti, Gianluca Setti
Design of Random Modulation Pre-Integration systems based on the restricted-isometry property may be suboptimal when the energy of the signals to be acquired is not evenly distribu…