Automation is changing the way businesses operate. From the factory floor to back-end IT, automated services and machines are increasing speed and productivity while freeing workers up to focus on more skilled tasks.

Automation is rule-based, whereas AI is trained to learn, develop and grow using the data it is given. An AI system is constantly in a state of change.

That means that artificial intelligence is a great fit for cyber security, where malicious actors are continuously developing new attacks. The old signature-based style of defence is no longer enough to protect companies’ data.

AI needed to keep up with modern threats

“Cyber-attackers are growing faster and more sophisticated by the day,” said Andrew Tsonchev, director of technology at Darktrace Industrial, the branch of the company that uses AI to secure industrial systems and critical national infrastructure.

“Organisations are facing everything from lightning-speed ransomware to stealthy ‘unknown unknowns’ that bypass traditional perimeter defences to silently carry out espionage over long periods of time. Human defenders simply cannot keep up with modern threats, especially as they manage increasingly complex networks.”

Several companies are now automating their security, while others are working in the more advanced realms of AI.

Human intervention still necessary

Tsonchev said: “In response to the global cyber struggle, the cyber security market is flourishing. ‘Machine learning’ and ‘AI’ have fast become industry buzzwords, but many innovations still require rules and signatures of previous attacks and human pre-programming to work. Developing technology that learns on-the-job in live networks is a difficult feat, and many fail outside the lab.”

“Even with automation, there still needs to be human oversight. Automating patching or change provisioning bring their specific risks to the equation that must be weighed against the reward of any potential time-savings. Considering errors that could be compounded via automated action and the potential for business disruption, a human element in these execution processes may still be best.”

Source: Computing