- Machine learning in healthcare cybersecurity is expected to increase spending on big data, intelligence, and analytics, according to a report by ABI Research.
Cyber threats are a constant concern for enterprises and are expected to cause over one trillion dollars in damages by 2018, the report predicted. To better defend against these attacks, cybersecurity vendors are considering machine learning to provide more dynamic and intuitive defenses.
The report suggests the machine learning cybersecurity market will boost the worth of big data, intelligence, and analytics spending to $96 billion by 2021.
"We are in the midst of an artificial intelligence security revolution," ABI Research Industry Analyst Dimitrios Pavlakis said in a statement. "This will drive machine learning solutions to soon emerge as the new norm beyond Security Information and Event Management (SIEM), and ultimately displace a large portion of traditional AV, heuristics, and signature-based systems within the next five years."
Report authors predict that user and entity behavioral analytics (UEBA) and deep learning algorithm designs are emerging as the two most popular cybersecurity artificial intelligence (AI) technologies.
Vendors are beginning to transform their solutions to accommodate UEBA and deep learning for the future of cybersecurity. Constantly shifting threats call for supervised models, unsupervised models, and semi-supervised models.
Currently SIEM technology is considered one of the most advanced types of infrastructure cybersecurity. SIEM aggregates event data from all solutions across an IT infrastructure and applies security analytics in real-time for the earliest possible security threat detection.
Introducing machine learning into enterprise cybersecurity will separate and integrate SIEM log-based methods with other UEBA. Machine learning will allow this process to be unsupervised, eliminating breaches caused by human error.
Machine learning has proved useful in healthcare analytics, with providers and vendors looking to apply the technology to security solutions to protect clinical health data store on-premise and in the cloud. Applying machine learning and AI to different health IT infrastructure solutions is going to transform healthcare. Machine learning and AI can automate processes at a much faster rate than is currently possible with staff monitoring every aspect of the network.
"This radical transformation is already underway and is occurring as a response to the increasingly menacing nature of unknown threats and multiplicity of threat agents," Pavlakis concluded.
IBM is already focused on bringing machine learning to healthcare cybersecurity with the launch of its AI cyber security beta program late last year.
IBM Watson for Cyber Security program intends to address the security challenges organizations face as IT infrastructures grow more advanced. Advanced technological environments drive the need for an intelligent means of identifying and prioritizing cyber threats.
The healthcare industry is seeing spikes in cognitive and AI solutions most prominently in the big data and analytics space, but Watson for Cyber Security could potentially bring a new AI use in the healthcare industry.
Watson for Cyber Security uses machine learning and natural language processing to assist IT professionals in making well-informed and timely decisions based on large amounts of structured and unstructured data.
"Customers are in the early stages of implementing cognitive security technologies," IBM Security Chief Technology Officer Sandy Bird said. "Our research suggests this adoption will increase threefold over the next three years, as tools like Watson for Cyber Security mature and become pervasive in security operations centers. Currently, only seven percent of security professionals claim to be using cognitive solutions."
The IBM Watson for Cybersecurity Program is currently being beta tested in 40 organizations across all major industries.
Healthcare organizations using IBM Watson for other initiatives may benefit from the results of the beta program by implementing machine learning techniques to their security measures.