"SAN FRANCISCO, Aug 8 (Reuters) - The nightmare scenario for computer security - artificial intelligence programs that can learn how to evade even the best defenses - may already have arrived. That warning from security researchers is driven home by a team from IBM Corp. who have used the artificial intelligence technique known as machine learning to build hacking programs that could slip past top-tier defensive measures. The group will unveil details of its experiment at the Black Hat security conference in Las Vegas on Wednesday..." http://news.trust.org/item/20180808095952-0398k
I think it is going to take AI to stop AI. This is why we are going to need enterprise level AI based anti-malware for home use, like Cylance home or better and perhaps AI based next-generation firewall appliances on our home gateways protecting all our devices sooner rather than later.
"'DeepLocker': IBM's proof-of-concept 'DeepLocker' malware uses AI to infect PCs Neural network hides its intent until it finds the right victim... The AI model will only 'unlock' the malware to begin the attack if it identifies certain criteria; these can be based on any number of attributes, including visual, audio, geolocation and system-level features. It's almost impossible to identify all possible triggers, making reverse-engineering the deep neural network (DNN) a difficult prospect... The clever part of IBM's work is that it has turned a traditional weakness of black box AI - the fact that you can't see inside to understand how it reaches its decisions - into a strength..." https://www.theinquirer.net/inquire...cept-deeplocker-malware-uses-ai-to-infect-pcs https://www.blackhat.com/us-18/brie...g-targeted-attacks-with-ai-locksmithing-11549 http://i.blackhat.com/us-18/Thu-Aug...ing-Targeted-Attacks-with-AI-Locksmithing.pdf
IBM Research: "DeepLocker: How AI Can Power a Stealthy New Breed of Malware..." https://securityintelligence.com/deeplocker-how-ai-can-power-a-stealthy-new-breed-of-malware/