By Fabio Roli and Matteo Mauri

In the first part of this article “Artificial Intelligence: past, present and future. Part I - Short history of Artificial Intelligence”, previously published in this blog, we tried to unpack the "suitcase" of Artificial Intelligence. Now we will discuss  the "good", "ugly" and "bad" aspects inside this “suitcase”. As the reader will immediately notice, the title is a small tribute to the famous movie by Sergio Leone. We are not the first to use this leitmotiv to talk about Artificial Intelligence. AI certainly has "good", "ugly" and "bad" aspects; highlighting these aspects can help to understand what is Artificial Intelligence today. Always bearing in mind that, as in the case of the three characters of the movie, the good, the bad and the ugly cannot be clearly separated.

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.

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.