Who remembers the Forbin Project* and doesn't forget Colossi?
Carmela Troncoso, head of the head of the Security and Privacy Engineering Laboratory at École Polytechnique Fédérale de Lausanne in Switzerland, also agreed, pointing out that not only was resilience an issue but questioning whether it was possible to build a machine-learning system that was explainable, fair, and privacy preserving as well.
Does that more than suggest, and who would disagree, that it is certainly possible to build a machine-learning system that was/is unexplainable [for fantastic stealth], unfair [for overwhelming advantage] and privacy busting [for no hidden dirty secrets to bugger up the machine learning].
Resilience then would not be an issue to worry oneself unnecessarily about.
And get used to what's on Whitfield Diffie's mind as shared in the four paragraphs under the sub-title, Privacy will be a myth for that boat sailed away ages ago and where it docked on its travels revealed for delivery all manner of exotic wares and erotic fare to trade and free enslaved populations with.
Whatever happened to Hugo de Garis? He seemed to know what he was talking about, and what we are here also talking about is not greatly dissimilar.
Hugo de Garis is a retired researcher in the sub-field of artificial intelligence known as evolvable hardware. He became known in the 1990s for his research on the use of genetic algorithms to evolve artificial neural networks using three-dimensional cellular automata inside field programmable gate arrays. ...... https://en.wikipedia.org/wiki/Hugo_de_Garis
* ....... If of a nervous and/or anxious disposition, beware.