b'Fabio Roli'

research

∙ 09/20/2023

3D Face Reconstruction: the Road to Forensics

3D face reconstruction algorithms from images and videos are applied to ...

0 Simone Maurizio La Cava, et al. ∙

research

∙ 09/19/2023

Adversarial Attacks Against Uncertainty Quantification

Machine-learning models can be fooled by adversarial examples, i.e., car...

0 Emanuele Ledda, et al. ∙

research

∙ 02/06/2023

Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks

Among Bayesian methods, Monte-Carlo dropout provides principled tools fo...

0 Emanuele Ledda, et al. ∙

research

∙ 12/12/2022

A Survey on Reinforcement Learning Security with Application to Autonomous Driving

Reinforcement learning allows machines to learn from their own experienc...

33 Ambra Demontis, et al. ∙

research

∙ 11/05/2022

Stateful Detection of Adversarial Reprogramming

Adversarial reprogramming allows stealing computational resources by rep...

0 Yang Zheng, et al. ∙

research

∙ 07/12/2022

Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

While machine learning is vulnerable to adversarial examples, it still l...

9 Luca Demetrio, et al. ∙

research

∙ 06/01/2022

Support Vector Machines under Adversarial Label Contamination

Machine learning algorithms are increasingly being applied in security-r...

11 Huang Xiao, et al. ∙

research

∙ 03/14/2022

Energy-Latency Attacks via Sponge Poisoning

Sponge examples are test-time inputs carefully-optimized to increase ene...

5 Antonio Emanuele Cinà, et al. ∙

research

∙ 03/07/2022

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

Adversarial patches are optimized contiguous pixel blocks in an input im...

50 Maura Pintor, et al. ∙

research

∙ 10/20/2021

Fingerprint recognition with embedded presentation attacks detection: are we ready?

The diffusion of fingerprint verification systems for security applicati...

0 Marco Micheletto, et al. ∙

research

∙ 10/12/2021

Can machines learn to see without visual databases?

This paper sustains the position that the time has come for thinking of ...

0 Alessandro Betti, et al. ∙

research

∙ 08/26/2021

Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference

Adversarial reprogramming allows repurposing a machine-learning model to...

20 Yang Zheng, et al. ∙

research

∙ 06/18/2021

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Evaluating robustness of machine-learning models to adversarial examples...

25 Maura Pintor, et al. ∙

research

∙ 06/14/2021

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions

Backdoor attacks inject poisoning samples during training, with the goal...

5 Antonio Emanuele Cinà, et al. ∙

research

∙ 05/02/2021

Intriguing Usage of Applicability Domain: Lessons from Cheminformatics Applied to Adversarial Learning

Defending machine learning models from adversarial attacks is still a ch...

10 Luke Chang, et al. ∙

research

∙ 03/23/2021

The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?

One of the most concerning threats for modern AI systems is data poisoni...

7 Antonio Emanuele Cinà, et al. ∙

research

∙ 02/25/2021

Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints

Evaluating adversarial robustness amounts to finding the minimum perturb...

14 Maura Pintor, et al. ∙

research

∙ 10/13/2020

Detecting Anomalies from Video-Sequences: a Novel Descriptor

We present a novel descriptor for crowd behavior analysis and anomaly de...

0 Giulia Orrù, et al. ∙

research

∙ 08/17/2020

Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection

Recent work has shown that adversarial Windows malware samples - also re...

0 Luca Demetrio, et al. ∙

research

∙ 07/07/2020

Are spoofs from latent fingerprints a real threat for the best state-of-art liveness detectors?

We investigated the threat level of realistic attacks using latent finge...

0 Roberto Casula, et al. ∙

research

∙ 06/06/2020

Can Domain Knowledge Alleviate Adversarial Attacks in Multi-Label Classifiers?

Adversarial attacks on machine learning-based classifiers, along with de...

16 Stefano Melacci, et al. ∙

research

∙ 05/25/2020

Adversarial Feature Selection against Evasion Attacks

Pattern recognition and machine learning techniques have been increasing...

8 Fei Zhang, et al. ∙

research

∙ 05/04/2020

Do Gradient-based Explanations Tell Anything About Adversarial Robustness to Android Malware?

Machine-learning algorithms trained on features extracted from static co...

3 Marco Melis, et al. ∙

research

∙ 03/30/2020

Efficient Black-box Optimization of Adversarial Windows Malware with Constrained Manipulations

Windows malware detectors based on machine learning are vulnerable to ad...

0 Luca Demetrio, et al. ∙

research

∙ 11/28/2019

A novel classification-selection approach for the self updating of template-based face recognition systems

The boosting on the need of security notably increased the amount of pos...

0 Giulia Orrù, et al. ∙

research

∙ 10/01/2019

Deep Neural Rejection against Adversarial Examples

Despite the impressive performances reported by deep neural networks in ...

47 Angelo Sotgiu, et al. ∙

research

∙ 09/16/2019

Towards Quality Assurance of Software Product Lines with Adversarial Configurations

Software product line (SPL) engineers put a lot of effort to ensure that...

0 Paul Temple, et al. ∙

research

∙ 03/27/2019

3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis

Face presentation attacks have become a major threat to face recognition...

0 Lei Li, et al. ∙

research

∙ 01/11/2019

Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binaries

Recent work has shown that deep-learning algorithms for malware detectio...

0 Luca Demetrio, et al. ∙

research

∙ 11/25/2018

Poisoning Behavioral Malware Clustering

Clustering algorithms have become a popular tool in computer security to...

0 Battista Biggio, et al. ∙

research

∙ 11/25/2018

Is Data Clustering in Adversarial Settings Secure?

Clustering algorithms have been increasingly adopted in security applica...

0 Battista Biggio, et al. ∙

research

∙ 10/31/2018

Face Presentation Attack Detection in Learned Color-liked Space

Face presentation attack detection (PAD) has become a thorny problem for...

0 Lei Li, et al. ∙

research

∙ 09/08/2018

On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks

Transferability captures the ability of an attack against a machine-lear...

0 Ambra Demontis, et al. ∙

research

∙ 05/30/2018

Towards Adversarial Configurations for Software Product Lines

Ensuring that all supposedly valid configurations of a software product ...

12 Paul Temple, et al. ∙

research

∙ 04/21/2018

Is feature selection secure against training data poisoning?

Learning in adversarial settings is becoming an important task for appli...

0 Huang Xiao, et al. ∙

research

∙ 03/12/2018

Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables

Machine-learning methods have already been exploited as useful tools for...

0 Bojan Kolosnjaji, et al. ∙

research

∙ 03/09/2018

Explaining Black-box Android Malware Detection

Machine-learning models have been recently used for detecting malicious ...

0 Marco Melis, et al. ∙

research

∙ 12/17/2017

Super-sparse Learning in Similarity Spaces

In several applications, input samples are more naturally represented in...

0 Ambra Demontis, et al. ∙

research

∙ 12/08/2017

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning

Learning-based pattern classifiers, including deep networks, have demons...

0 Battista Biggio, et al. ∙

research

∙ 08/23/2017

Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid

Deep neural networks have been widely adopted in recent years, exhibitin...

0 Marco Melis, et al. ∙

research

∙ 09/06/2016

Review of the Fingerprint Liveness Detection (LivDet) competition series: 2009 to 2015

A spoof attack, a subset of presentation attacks, is the use of an artif...

0 Luca Ghiani, et al. ∙

research

∙ 09/06/2016

Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems

Prior work has shown that multibiometric systems are vulnerable to prese...

0 Battista Biggio, et al. ∙

research

∙ 05/12/2011

A Multiple Component Matching Framework for Person Re-Identification

Person re-identification consists in recognizing an individual that has ...

0 Riccardo Satta, et al. ∙

Fabio Roli

Featured Co-authors