Machine Learning to Ward off Cyber Threats
Machine learning is increasingly being used for cyber security purposes to provide a more dynamic deterrent to cyber threats, according to a study report by ABI Research titled “Machine Learning in Cybersecurity Technologies.” The high adoption of machine learning in government, defense, banking and technology sectors, has set the trend, leading ABI Research to predict that global spending on big data, analytics and intelligence would touch $96 billion by 2021.
Machine learning is artificial intelligence (AI) used by computers to learn on their own. The computer programs have an in-built ability to change when they are exposed to new data.
“We are in the midst of an artificial intelligence security revolution,” says Dimitrios Pavlakis, Industry Analyst, ABI Research. “This will drive machine learning solutions to soon emerge as the new norm beyond Security Information and Event Management, or SIEM, and ultimately displace a large portion of traditional AV, heuristics and signature-based systems, within the next five years.”
Some of the key findings of the study are:
- Prominent technologies which had the highest adoption of machine learning for cyber security were User and Entity Behavioral Analytics (UEBA) and Deep Learning algorithm designs.
- Innovative tech start-ups were majorly using UEBA and Deep Learning algorithm designs.
- Established vendors in the anti-virus market like Symantec, are transforming their solutions from supervised models which were highly trained to semi-supervised and unsupervised models.
- Signature-based anti-virus systems would be completely absorbed and become a sub-section of supervised machine learning models.
- Security Information and Event Management (SIEM) software services and products combine Security Event Management (SEM) with Security Information Management (SIM). In the future, the log-based methods of SIEM would be separated and integrated within UEBA, deep learning and unsupervised solutions.
- Some of the prominent vendors employing machine learning technologies for cyber security purposes include IBM, Symantec, Niara, Splunk, Sqreen, Vectra Networks, Gurucul, StatusToday, Trudera, Deep Instinct, SparkCognition and Jask.
- IBM is majorly transforming the way machine learning is employed by organizations across sectors, which also includes cyber security.
- Companies attempting innovative UEBA applications include Gurucul, Niara, StatusToday, Splunk, Trudera and Vectra Networks.
- Companies like Spark Cognition and Deep Instinct are providing solutions that use deep learning, feature-agnostic models and natural language processing.
“This radical transformation is already under way and is occurring as a response to the increasingly menacing nature of unknown threats and multiplicity of threat agents,” concludes Pavlakis. “The proliferation of machine learning is also causing an explosion of agile start-ups, such as JASK, focusing more on SIEM complementary network traffic analysis and even pioneering application protection such as Sqreen.”
Found this post useful? Kindly tap the ❤ button below! :)
About Read IT Quik
ReadITQuik offers a platform for IT professionals and decision-makers to stay connected with the latest developments in the tech world, and follow hot topics and trends. You can connect with us on Twitter, LinkedIn and Facebook