The founder of Adversa delivered a talk titled ‘AI Security: Why, What, How’ at the HITB Conference. HITBSecConf is an annual must-attend event in the calendars of security researchers and professionals around the world. It is a platform for the discussion and dissemination of next-generation computer security issues. Now, these issues address artificial intelligence, which is steadily flooding our world and slipping into a lot of verticals. While we understand more or less how to deal with software vulnerabilities, we have no clue what’s happening in ML-based solutions. We cannot but take note of adversarial examples, which have recently attracted media attention but were invented 5 years ago. Alexander told about the industry of AI security and the most critical AI applications such as face recognition, self-driving cars, voice assistants, and the latest attacks. Particular attack methods like adversarial, privacy, poisoning, backdoor, reprogramming were discussed. The video is available on YouTube.