Increased reliance on AI and Machine Learning

According to latest Cisco 2018 Annual Cybersecurity Report (ACR), malware sophistication is increasing as adversaries begin to weaponize cloud services and evade detection through encryption, used as a tool to conceal command-and-control activity. As per the report, security professionals said to reduce adversaries’ time to operate they will increasingly leverage and spend more on tools that use AI and machine learning.

While encryption is meant to enhance security, the expanded volume of encrypted web traffic (50 percent as of October 2017) — both legitimate and malicious — has created more challenges for defenders trying to identify and monitor potential threats. Cisco threat researchers observed more than a threefold increase in encrypted network communication used by inspected malware samples over a 12-month period.

Applying machine learning can help enhance network security defenses and, over time, “learn” how to automatically detect unusual patterns in encrypted web traffic, cloud, and IoT environments. Some of the 3,600 chief information security officers (CISOs) interviewed for the Cisco 2018 Security Capabilities Benchmark Study report, stated they were reliant and eager to add tools like machine learning and AI, but were frustrated by the number of false positives such systems generate. While still in its infancy, machine learning and AI technologies over time will mature and learn what is “normal” activity in the network environments they are monitoring.

“Last year’s evolution of malware demonstrates that our adversaries continue to learn,” said Scott Manson, Cybersecurity Lead – Middle East and Africa at Cisco. “We have to raise the bar now – top down leadership, business led, technology investments, and practice effective security – there is too much risk, and it is up to us to reduce it.”

The report also claimed that the financial cost of attacks is no longer a hypothetical number rather it said more than half of all attacks resulted in financial damages of more than US$500,000, including, but not limited to, lost revenue, customers, opportunities, and out-of-pocket costs.

These attacks can impact computers on a massive scale and can persist for months or even years. Defenders should be aware of the potential risk of using software or hardware from organizations that do not appear to have a responsible security posture.

Security is getting more complex, scope of breaches is expanding and in 2017, 25 percent of security professionals said they used products from 11 to 20 vendors, compared with 18 percent of security professionals in 2016 and 32 percent of breaches affected more than half of their systems, compared with 15 percent in 2016.

92 percent of security professionals said behavior analytics tools work well. Two-thirds of the healthcare sector, followed by financial services, found behavior analytics to work extremely well to identify malicious actors.

Use of cloud is growing, attackers are taking advantage of the fact that security teams are having difficulty defending evolving and expanding cloud environments. The combination of best practices, advanced security technologies like machine learning, and first-line-of-defense tools like cloud security platforms can help protect this environment.

Trends in malware volume have an impact on defenders’ time to detection (TTD) and the Cisco median TTD of about 4.6 hours for the period from November 2016 to October 2017 — well below the 39-hour median TTD reported in November 2015, and the 14-hour median reported in the Cisco 2017 Annual Cybersecurity Report for the period from November 2015 to October 2016.

The report discusses how the use of cloud-based security technology has been a key factor in helping Cisco to drive and keep its median TTD to a low level. Faster TTD helps defenders move sooner to resolving breaches.