160 citations · 610 across the 19 of their papers we have counts for
23 papers
Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer +1
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Opti…
FedRAD: Federated Robust Adaptive Distillation
Stefán Páll Sturluson, Samuel Trew, Luis Muñoz-González +4
The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients. The collaborative learning…
Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer +1
Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current a…
Real-time Detection of Practical Universal Adversarial Perturbations
Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan +1
Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attac…
Realizable Universal Adversarial Perturbations for Malware
Raphael Labaca-Castro, Luis Muñoz-González, Feargus Pendlebury +3
Machine learning classifiers are vulnerable to adversarial examples -- input-specific perturbations that manipulate models' output. Universal Adversarial Perturbations (UAPs), whic…
Robustness and Transferability of Universal Attacks on Compressed Models
Alberto G. Matachana, Kenneth T. Co, Luis Muñoz-González +2
Neural network compression methods like pruning and quantization are very effective at efficiently deploying Deep Neural Networks (DNNs) on edge devices. However, DNNs remain vulne…
Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare
Matei Grama, Maria Musat, Luis Muñoz-González +3
Federated learning (FL) has enabled training models collaboratively from multiple data owning parties without sharing their data. Given the privacy regulations of patient's healthc…
Non-equilibrium effective field theory and second sound
Michael J. Landry
We investigate the phenomenon of second sound in various states of matter from the perspective of non-equilibrium effective field theory (EFT). In particular, for each state of mat…
Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer +1
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Opti…
Universal Adversarial Robustness of Texture and Shape-Biased Models
Kenneth T. Co, Luis Muñoz-González, Leslie Kanthan +2
Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture a…
Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
Luis Muñoz-González, Kenneth T. Co, Emil C. Lupu
Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learni…
Sensitivity of Deep Convolutional Networks to Gabor Noise
Kenneth T. Co, Luis Muñoz-González, Emil C. Lupu
Deep Convolutional Networks (DCNs) have been shown to be sensitive to Universal Adversarial Perturbations (UAPs): input-agnostic perturbations that fool a model on large portions o…
Poisoning Attacks with Generative Adversarial Nets
Luis Muñoz-González, Bjarne Pfitzner, Matteo Russo +2
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the…
Efficient attack countermeasure selection accounting for recovery and action costs
Jukka Soikkeli, Luis Muñoz-González, Emil C. Lupu
The losses arising from a system being hit by cyber attacks can be staggeringly high, but defending against such attacks can also be costly. This work proposes an attack countermea…
Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Convolutional Networks
Kenneth T. Co, Luis Muñoz-González, Sixte de Maupeou +1
Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning a…
Mitigation of Adversarial Attacks through Embedded Feature Selection
Ziyi Bao, Luis Muñoz-González, Emil C. Lupu
Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it…
Approaches to Enhancing Cyber Resilience: Report of the North Atlantic Treaty Organization (NATO) Workshop IST-153
Alexander Kott, Benjamin Blakely, Diane Henshel +21
This report summarizes the discussions and findings of the 2017 North Atlantic Treaty Organization (NATO) Workshop, IST-153, on Cyber Resilience, held in Munich, Germany, on 23-25…
Label Sanitization against Label Flipping Poisoning Attacks
Andrea Paudice, Luis Muñoz-González, Emil C. Lupu
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in…
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Andrea Paudice, Luis Muñoz-González, Andras Gyorgy +1
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among other…
Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
Luis Muñoz-González, Battista Biggio, Ambra Demontis +4
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of d…
Automated Dynamic Analysis of Ransomware: Benefits, Limitations and use for Detection
Daniele Sgandurra, Luis Muñoz-González, Rabih Mohsen +1
Recent statistics show that in 2015 more than 140 millions new malware samples have been found. Among these, a large portion is due to ransomware, the class of malware whose specif…
Efficient Attack Graph Analysis through Approximate Inference
Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice +1
Attack graphs provide compact representations of the attack paths that an attacker can follow to compromise network resources by analysing network vulnerabilities and topology. The…
Exact Inference Techniques for the Analysis of Bayesian Attack Graphs
Luis Muñoz-González, Daniele Sgandurra, Martín Barrère +1
Attack graphs are a powerful tool for security risk assessment by analysing network vulnerabilities and the paths attackers can use to compromise network resources. The uncertainty…