activity
20172026
most citedEvasion Attacks against Machine Learning at Test Time

889 citations · 1.7k across the 37 of their papers we have counts for

collaborators
Showing 2023Show all

8 papers · 1 filter

cs.CR202311 cited

Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors

Biagio Montaruli, Luca Demetrio, Maura Pintor +3

Machine-learning phishing webpage detectors (ML-PWD) have been shown to suffer from adversarial manipulations of the HTML code of the input webpage. Nevertheless, the attacks recen…

cs.LG20231 cited

Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

Giuseppe Floris, Raffaele Mura, Luca Scionis +4

Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fas…

cs.LG2023

Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

Giorgio Piras, Maura Pintor, Ambra Demontis +1

Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks…

cs.CR2023

Nebula: Self-Attention for Dynamic Malware Analysis

Dmitrijs Trizna, Luca Demetrio, Battista Biggio +1

Dynamic analysis enables detecting Windows malware by executing programs in a controlled environment and logging their actions. Previous work has proposed training machine learning…

cs.CV20231 cited

Adversarial Attacks Against Uncertainty Quantification

Emanuele Ledda, Daniele Angioni, Giorgio Piras +3

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantifi…

cs.CV2023

Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks

Yang Zheng, Luca Demetrio, Antonio Emanuele Cinà +6

RGB-D object recognition systems improve their predictive performances by fusing color and depth information, outperforming neural network architectures that rely solely on colors.…