From Cybersecurity with Stuart McClure Cylance (CxOTalk #324) · · CXOTalk
“It really is one of the areas, when you ask me what keeps me up at night ... it's probably massive cyberattacks as a precursor to something far worse in the physical world like precursor to war by attacking the electric grid. Keeping the electric grid down for weeks at a time would be an incredible precursor to something very, very bad.”
On , Stuart Mcclure, Cofounder at Cylance, spoke about critical infrastructure during Cybersecurity with Stuart McClure Cylance (CxOTalk #324) on CXOTalk.
Stuart McClure, co-founder and CEO of Cylance, has discussed the company's use of machine learning and mathematical models to prevent cyberattacks. In a 2019 interview, he stated that traditional signature-based approaches are 30% to 50% effective on new attacks, while AI and machine learning approaches achieve a 99.9% effectiveness rate. He described Cylance's technology as using feature extraction from files to train models that classify software as good or bad, allowing endpoints to operate autonomously without cloud connectivity. McClure also warned about the potential for "adversarial AI" or "AI versus AI" attacks, though he noted that such sophisticated attacks had not yet been observed in the wild as of 2019. In a 2015 keynote, McClure argued that the cybersecurity industry has historically been reactive and urged audiences to "trust the math" rather than vendors. He described Cylance's process of collecting over eight terabytes of data and mapping over five million features to detect malicious files. McClure also highlighted concerns about cyberattacks targeting critical infrastructure, such as the electric grid, which he described as a potential precursor to physical conflict. He referenced the Stuxnet virus as an example of a state-sponsored attack on nuclear facilities.