no code implementations • 14 May 2024 • Yacine Izza, Xuanxiang Huang, Antonio Morgado, Jordi Planes, Alexey Ignatiev, Joao Marques-Silva
Logic-based XAI represents a rigorous approach to explainability; it is model-based and offers the strongest guarantees of rigor of computed explanations.
Adversarial Robustness Explainable artificial intelligence +1
no code implementations • 1 May 2024 • Daniel Gibert, Luca Demetrio, Giulio Zizzo, Quan Le, Jordi Planes, Battista Biggio
As a consequence, the injected content is confined to an integer number of chunks without tampering the other chunks containing the real bytes of the input examples, allowing us to extend our certified robustness guarantees to content insertion attacks.
1 code implementation • IEEE Access 2024 • Daniel Gibert, Giulio Zizzo, Quan Le, Jordi Planes
Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-art evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.
no code implementations • 23 Feb 2024 • Daniel Gibert, Giulio Zizzo, Quan Le, Jordi Planes
Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-are evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.
no code implementations • 27 Jun 2023 • Ramón Béjar, António Morgado, Jordi Planes, Joao Marques-Silva
The paper shows that most of the algorithms proposed in recent years for computing logic-based explanations can be generalized for computing explanations given the partially specified inputs.
1 code implementation • 27 Oct 2022 • Xuanxiang Huang, Martin C. Cooper, Antonio Morgado, Jordi Planes, Joao Marques-Silva
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction.
1 code implementation • 28 Sep 2020 • Daniel Gibert, Carles Mateu, Jordi Planes
Malware detection and classification is a challenging problem and an active area of research.
1 code implementation • 12 May 2020 • Daniel Gibert, Carles Mateu, Jordi Planes
While traditional machine learning methods for malware detection largely depend on hand-designed features, which are based on experts’ knowledge of the domain, end-to-end learning approaches take the raw executable as input, and try to learn a set of descriptive features from it.
no code implementations • 30 Sep 2019 • Daniel Gibert, Carles Mateu, Jordi Planes
Novel approaches in the literature treat an executable as a sequence of bytes or as a sequence of assembly language instructions.
no code implementations • 27 Sep 2018 • Daniel Gibert, Carles Mateu, Jordi Planes
In traditional machine learning techniques for malware detection and classification, significant efforts are expended on manually designing features based on expertise and domain-specific knowledge.
1 code implementation • 27 Apr 2018 • Daniel Gibert, Carles Mateu, Jordi Planes, Ramon Vicens
Motivated by the visual similarity between streams of entropy of malicious software belonging to the same family, we propose a file agnostic deep learning approach for categorization of malware.
Ranked #5 on Malware Classification on Microsoft Malware Classification Challenge (LogLoss metric)
1 code implementation • 27 Oct 2017 • Daniel Gibert, Javier Béjar, Carles Mateu, Jordi Planes, Daniel Solis, Ramon Vicens
Traditional signature-based methods have started becoming inadequnate to deal with next generation malware which utilize sophisticated obfuscation (polymorphic and metamorphic) techniques to evade detection.