This thesis proposes a security by design framework for identifying and mitigating cyber and
physical threats on CAVs. A structured security engineering process for threat identification …

The simplest definition of machine learning (ML) is “the ability for computers to acquire
knowledge without being explicitly programmed.” With the aid of statistical models applied …

The increasing use of data-centric approaches in the fields of Machine Learning and
Artificial Intelligence (ML/AI) has raised substantial issues over the security, integrity, and …

Neste artigo, analisamos experimentalmente sete conjuntos de dados e três modelos de ML
no contexto de três ataques de inversão de rótulos, organizados em seis taxas de ruído de …

Data mining is being applied to lots of applications scenarios. For instance, this paper
studies the realization of the auxiliary design platform for the manufacturing NC machining …

With the technological advancement, the world is going through, at such a high pace, new
challenges arise that might require new approaches. ML is, without a doubt, on the lead of …

We propose a novel discrete-time dynamical system-based framework for achieving
adversarial robustness in machine learning models. Our algorithm is originated from robust …

ABSTRACT Currently, Machine Learning (ML) is becoming ubiquitous in everyday life. Deep
Learning (DL) is already present in many applications ranging from computer vision for …

Good machine learning models are evidently available in the literature. More research
towards even improved versions of these machine learning models is still on going …