Home News Deep learning delivers proactive cyber defense

Deep learning delivers proactive cyber defense


High-profile threats, such as ransomware, saw double-digit growth (15.8%). The result is a perilous path that will most likely result in continued losses for organizations that fall victim to cyberattacks with no gain in defensive capabilities. In fact, the 2021 data breach report from IBM and the Ponemon Institute shows that the average cost of a data breach is $4.24 million.

In addition to cost, a cyberattack can cause irreparable damage to a company’s brand, stock price, and day-to-day operations. According to a recent Deloitte survey, 32 percent of respondents cited operational disruption as the biggest impact of a cyber incident or breach. Other impacts cited by the companies surveyed included intellectual property theft (22%), share price declines (19%), reputational loss (17%) and loss of customer trust (17%).

Given these significant risks, organizations simply cannot accept the status quo of protecting digital assets. “If we’re going to outperform our adversaries, the world needs to shift its mindset from detection to prevention,” Kaspi said. “Organizations need to change the way they enforce security and combat hacking.”

Deep learning may be different

To date, many cybersecurity experts see machine learning as the most innovative way to protect digital assets. But deep learning is great for changing the way we prevent cybersecurity attacks. Any machine learning tool can be understood and theoretically reverse engineered to introduce biases or vulnerabilities that would weaken its defenses against attacks. Bad actors can also contaminate defense solutions with fake datasets using their own machine learning algorithms.

Fortunately, deep learning addresses the limitations of machine learning by circumventing the need for highly skilled and experienced data scientists to manually provide solution datasets. Instead, deep learning models developed specifically for cybersecurity can ingest and process large amounts of raw data to adequately train the system. These neural networks become autonomous once trained and do not require constant human intervention. The combination of this raw-data-based learning approach and larger datasets means that deep learning can finally accurately identify more complex patterns at a faster rate than machine learning.

“Deep learning trumps any deny list, heuristic or standard machine learning approach,” said Mirel Sehic, vice president and general manager of Honeywell Building Technologies (HBT), a multinational company that provides aerospace, high-performance materials, Safety and productivity technology. “Deep learning-based methods take much faster time to detect a specific threat than any of these elements combined.”

Download the full report.

This content is produced by Insights, the custom content arm of MIT Technology Review. It was not written by the editorial staff of MIT Technology Review.

Source link

Previous articlePrabhas’ Next With RRR Makers To Have No Actress From Bollywood? Actor Gives 100 Days To The Shoot!
Next articleAllu Arjun Talks About His Bollywood Debut


Please enter your comment!
Please enter your name here