Deep learning provides proactive cyber defense

Increasing the rate of high-profile threats (such as ransomware) to doublefigure (15.8%) growth. The result is a dangerous path that is likely to lead to permanent losses for organizations that fall victim to a cyber attack without any strengthening of the defensive forces. Indeed, the 2021 IBM and Ponemon Institute data breach report shows that the average cost of a data breach is $4.24 million.

In addition to costs, a cyberattack can cause irreparable damage to a company’s brand, stock price, and day-to-day operations. According to a recent Deloitte report interview32% of respondents cited operational disruptions as the biggest impact of cyber incidents or hacks. Other impacts cited by surveyed companies include intellectual property theft (22%), a drop in share price (19%), loss of reputation (17%), and loss of customer confidence (17%).

Given these significant risks, organizations simply cannot afford to accept the status quo regarding digital asset protection. “If we are ever to get ahead of our adversaries, the world must change its mindset from detection to prevention,” Kaspi says. “Organizations need to change the way they manage security and fight hackers.”

Deep learning can be the difference

Until now, many cybersecurity experts have considered machine learning as the most innovative approach to protecting digital assets. But deep learning is ideal for changing the way cyberattacks are prevented. Any machine learning tool can be understood and theoretically redesigned to introduce a bias or vulnerability that weakens its defense against attack. Attackers can also use their own machine learning algorithms to pollute a security solution with false datasets.

Fortunately, deep learning removes the limitations of machine learning by bypassing the need for highly trained and experienced data scientists to manually load a dataset for a solution. Rather, a deep learning model specifically designed for cybersecurity can ingest and process massive amounts of raw data to fully train the system. These neural networks become autonomous after training and do not require constant human intervention. This combination of raw data learning methodology and large datasets means that deep learning will eventually be able to accurately identify much more complex patterns than machine learning at much faster speeds.

“Deep learning overshadows any do-nothing, heuristic, or standard approach to machine learning,” says Mirel Sehik, vice president, general manager of Honeywell Building Technologies (HBT), a multinational corporation and supplier of aerospace, high performance materials, and security and performance technologies. technology. “The time it takes for a deep learning approach to detect a specific threat is much faster than any of these elements combined.”

Download full report.

This content was prepared by Insights, the user-generated content division of MIT Technology Review. This was not written by the editors of the MIT Technology Review.

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button