The need to protect the AI ​​itself from attacks

[sumaiyakhatun26]

I confirm my consent to the processing of personal data

It is worth noting another important point related to the cybersecurity of artificial intelligence itself, i.e. when artificial intelligence itself acts as an object of protection or attack (depending on which side you look at it from).

And how does this differ from the problem of protecting classical (non-intelligent) information systems? The fact is that in the case of classical information systems, measures to ensure their cybersecurity are aimed, first of all france email list , at ensuring the availability of the system itself and the data, as well as at ensuring the integrity and confidentiality of the processed data. And in the case of artificial intelligence systems (services), more priority protective measures arise, aimed at ensuring conscientious training and correct decision-making by artificial intelligence.

Here, malicious attacks on the data used for training, attacks on algorithms and specific methods of their implementation, as well as on the entire infrastructure supporting the functioning of artificial intelligence systems (services) are possible. It is in this context that we talk about adversarial machine learning.

We give a discount of 60% on courses from GeekBrains until January 26
In just 9 months you will be able to get a job with an income of 150,000 rubles
Book a discount