Webinar "Machine Learning Security: Natural Problems of Artificial Intelligence"
On March 21, Digital Security experts will present their critical view on the widespread introduction of artificial intelligence (AI) and machine learning (MO). No matter how idealized the possibilities of AI are idealized today, it is an algorithm capable of making mistakes, and not check and alternative methods of solving a problem. We will discuss the specific vulnerabilities of the algorithms, identify the resulting reputational and financial risks and ways to increase the stability of the algorithms.
In the webinar program: ')
AI and MO in the modern world: the scope of use, the range of tasks;
Real cases of error algorithms and the problems that they entail;
Adversarial attacks on algorithms;
Ways to improve the stability of algorithms, methods of protection.
The webinar will be useful:
Heads of companies, IT directors and development directors considering and implementing AI technologies;
Technical specialists working with AI and MO algorithms;
Representatives of a wide audience interested in questions of AI.