by Futurism
Google Brain and data science platform Kaggle have announced an “AI Fight Club” to train machine learning systems on how to combat malicious AI. As computer systems become smarter, cyberattacks also become tougher to defend against, and this contest could help illuminate unforeseen vulnerabilities. This AI fight club will feature three adversarial challenges. The first (non-targeted adversarial attack) involves getting algorithms to confuse a machine learning system so it won’t work properly. Another battle (targeted adversarial attack) requires training one AI to force another to classify data incorrectly. The third challenge (defense against adversarial attacks) focuses on beefing up a smart system’s defenses.
https://futurism.com/googles-ai-fight-club-will-train-systems-to-defend-against-future-cyberattacks/
Share on Facebook