‘The History of Adversarial AI’ talk at HITB

Alex Polyakov and Eugene Neelou talked about the history of AI security at the HITB security conference.

HITBSecConf or the Hack In The Box Security Conference is an annual must-attend event in the calendars of security researchers and professionals around the world. Held annually in Kuala Lumpur, Malaysia, and Amsterdam in The Netherlands, HITBSecConf is a platform for the discussion and dissemination of next-generation computer security issues. Our events routinely feature two days of trainings and a two-day multi-track conference featuring cutting-edge hardcore technical talks delivered by some of the most respected names in the computer security industry. HITBSecConf is a place where ideas are exchanged, talent discovered and genius celebrated.

The threat landscape is changing, and hackers will use new techniques to tamper with AI solutions such as self-driving cars, facial recognition systems, drones, voice assistants, robots, financial algorithms, and other solutions, which will use machine learning or AI. Most of the mentioned AI solutions were analyzed with a focus on cybersecurity, and they appeared to be vulnerable. 

The research Alex and Eugene considered, aims at telling people about AI security from 2004 (the moment it was first introduced) till today. The goal is to make companies aware of insecure and malicious AI by sharing insights formed based on almost 2000 research papers.