428 citations · 763 across the 12 of their papers we have counts for
14 papers
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
Luca Scionis, Luca Melis, Maura Pintor +5
Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget and on a selective choice of pertur…
On the Robustness of Adversarial Training Against Uncertainty Attacks
Emanuele Ledda, Giovanni Scodeller, Daniele Angioni +5
In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of i…
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…
Dropout Injection at Test Time for Post Hoc Uncertainty Quantification in Neural Networks
Emanuele Ledda, Giorgio Fumera, Fabio Roli
Among Bayesian methods, Monte-Carlo dropout provides principled tools for evaluating the epistemic uncertainty of neural networks. Its popularity recently led to seminal works that…
Deep Neural Rejection against Adversarial Examples
Angelo Sotgiu, Ambra Demontis, Marco Melis +4
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples t…
Is feature selection secure against training data poisoning?
Huang Xiao, Battista Biggio, Gavin Brown +3
Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation o…