4 papers
A unifying Bayesian framework for adversarial robustness
Pablo G. Arce, Roi Naveiro, David RÃos Insua
The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge. Traditional defenses, such as adversarial training, typically ro…
Random points on with small logarithmic energy
Ujué Etayo, Pablo G. Arce
We analyse several constructions of random point sets on the sphere evaluating and comparing them through their discrete logarithmic energy: \be…
Evasion Attacks Against Bayesian Predictive Models
Pablo G. Arce, Roi Naveiro, David RÃos Insua
There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has…
Supporting product launching decisions with adversarial risk analysis
Pablo G. Arce, Sonali Das, David RÃos Insua
In a world of utility-driven marketing, each company acts as an adversary to other contenders, with all having competing interests. A major challenge for companies launching a new…