Valutazione attuale: 5 / 5

By Fabio Roli and Matteo Mauri

Marvin Minsky, one of the fathers of Artificial Intelligence, defined intelligence as a "suitcase word" which can lead to ambiguity and confusion, if we do not clarify in what sense we speak of "intelligence". For the same reason, writing a non-technical article on Artificial Intelligence is always a risk, especially for a technical person, and especially nowadays that the term “Artificial Intelligence” is, more than ever, a "suitcase" in which everybody puts a bit of everything. In this post, we will try to unpack this suitcase and to reorder the stuff inside, at least a little.

Visite: 6151

Leggi tutto...

Valutazione attuale: 5 / 5

By Battista Biggio and Matteo Mauri

We know, this is an ill-posed question. It cannot be shown that a system is secure, if not with respect to a precise attack model and under very specific assumptions. It is instead possible to demonstrate, in a much clearer way, when a system is vulnerable, and this is what we will try to do in this article, in relation to Artificial Intelligence (AI) systems.

It is quite known that the security of a system depends solely on the strength of its weakest link. AI is now pervasive and integrated in a transparent way in many different application scenarios and deployed systems. From the viewpoint of computer security, it is therefore legitimate to ask ourselves if AI algorithms themselves do not introduce novel vulnerabilities in such systems, potentially becoming the weakest link in the corresponding security chain.

Visite: 9509

Leggi tutto...