277 citations · 930 across the 33 of their papers we have counts for
12 papers · 1 filter
Underwater image filtering: methods, datasets and evaluation
Chau Yi Li, Riccardo Mazzon, Andrea Cavallaro
Underwater images are degraded by the selective attenuation of light that distorts colours and reduces contrast. The degradation extent depends on the water type, the distance betw…
Probabilistic Radio-Visual Active Sensing for Search and Tracking
L. Varotto, A. Cenedese, A. Cavallaro
Active Search and Tracking for search and rescue missions or collaborative mobile robotics relies on the actuation of a sensing platform to detect and localize a target. In this pa…
FoolHD: Fooling speaker identification by Highly imperceptible adversarial Disturbances
Ali Shahin Shamsabadi, Francisco Sepúlveda Teixeira, Alberto Abad +3
Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclassification. In this work, we propose a white-…
Robust Latent Representations via Cross-Modal Translation and Alignment
Vandana Rajan, Alessio Brutti, Andrea Cavallaro
Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning meth…
Benchmark for Anonymous Video Analytics
Ricardo Sanchez-Matilla, Andrea Cavallaro
Out-of-home audience measurement aims to count and characterize the people exposed to advertising content in the physical world. While audience measurement solutions based on compu…
Semantically Adversarial Learnable Filters
Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro
We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework comb…
DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data
Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro +1
Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates, enabling several applications, such as power management and…
Exploiting vulnerabilities of deep neural networks for privacy protection
Ricardo Sanchez-Matilla, Chau Yi Li, Ali Shahin Shamsabadi +2
Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were n…
Towards robust sensing for Autonomous Vehicles: An adversarial perspective
Apostolos Modas, Ricardo Sanchez-Matilla, Pascal Frossard +1
Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions. Fundamental building blocks of such systems are…
Novel-View Human Action Synthesis
Mohamed Ilyes Lakhal, Davide Boscaini, Fabio Poiesi +2
Novel-View Human Action Synthesis aims to synthesize the movement of a body from a virtual viewpoint, given a video from a real viewpoint. We present a novel 3D reasoning to synthe…
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas +4
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neur…
PrivEdge: From Local to Distributed Private Training and Prediction
Ali Shahin Shamsabadi, Adria Gascon, Hamed Haddadi +1
Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user…