Search Results for author: Giulio Lovisotto

Found 9 papers, 6 papers with code

Biometric Backdoors: A Poisoning Attack Against Unsupervised Template Updating

1 code implementation22 May 2019 Giulio Lovisotto, Simon Eberz, Ivan Martinovic

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update procedure.

Cryptography and Security

Seeing Red: PPG Biometrics Using Smartphone Cameras

1 code implementation15 Apr 2020 Giulio Lovisotto, Henry Turner, Simon Eberz, Ivan Martinovic

PPG signals are obtained by recording a video from the camera as users are resting their finger on top of the camera lens.

SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbations

1 code implementation8 Jul 2020 Giulio Lovisotto, Henry Turner, Ivo Sluganovic, Martin Strohmeier, Ivan Martinovic

Research into adversarial examples (AE) has developed rapidly, yet static adversarial patches are still the main technique for conducting attacks in the real world, despite being obvious, semi-permanent and unmodifiable once deployed.

Object Detection Traffic Sign Recognition

Speaker Anonymization with Distribution-Preserving X-Vector Generation for the VoicePrivacy Challenge 2020

1 code implementation26 Oct 2020 Henry Turner, Giulio Lovisotto, Ivan Martinovic

In this paper, we present a Distribution-Preserving Voice Anonymization technique, as our submission to the VoicePrivacy Challenge 2020.

They See Me Rollin': Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors

1 code implementation25 Jan 2021 Sebastian Köhler, Giulio Lovisotto, Simon Birnbach, Richard Baker, Ivan Martinovic

We validate our model against empirical data collected on two separate cameras, showing that by simply using information from the camera's datasheet the adversary can accurately predict the injected distortion size and optimize their attack accordingly.

object-detection Object Detection

Widen The Backdoor To Let More Attackers In

no code implementations9 Oct 2021 Siddhartha Datta, Giulio Lovisotto, Ivan Martinovic, Nigel Shadbolt

As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other.

Backdoor Attack

2-hop Neighbor Class Similarity (2NCS): A graph structural metric indicative of graph neural network performance

no code implementations26 Dec 2022 Andrea Cavallo, Claas Grohnfeldt, Michele Russo, Giulio Lovisotto, Luca Vassio

In this work, we highlight the limitations of the widely used homophily ratio and the recent Cross-Class Neighborhood Similarity (CCNS) metric in estimating GNN performance.

Node Classification

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