Impressive! SE Labs threat prevention evaluation of Deep Instinct

NEW YORK, N.Y. – April 10, 2019 – According to the latest test results from SE Labs’ independent threat prevention evaluation lab, Deep Instinct’s D-Client (v2.2.1.5) achieved a 100% prevention rate and zero false-positives – when detecting and blocking known and unknown cyber threats, including file-based and file-less attacks. The independent results also highlighted Deep Instinct’s ability to provide a wide range of detection and threat blocking capabilities without interfering with system performance.

Powering Deep Instinct’s D-Client is a deep learning-based malware detection and prevention engine,
D-Brain, which was trained in August 2018, six months prior to the customized-targeted threats being created. However, D-Client was still able to successfully detect and prevent all attacks. By leveraging D-Brain’s proprietary deep neural network architecture – revered for the best accuracy in known and unknown malware detection and prevention – all threats were successfully prevented pre-execution with no other processes running.

"SE Labs' tests are renowned for being technically challenging and in-depth. It's rare to achieve 100 percent ratings, which is precisely what Deep Instinct has done with its D-Client solution," said Simon Edwards, CEO of SE Labs and chairman of the board of the Anti-Malware Testing Standards Organization (AMTSO). "It's impressive that the company's technology was capable not only of blocking all of the advanced threats, but to do so with zero false positives."

As the first company to apply deep learning to cybersecurity, Deep Instinct leverages the power of deep learning’s predictive capabilities to create the ultimate zero-time threat prevention platform and network, which involves multi-layer protection across all endpoints, servers, mobile devices and operating systems (Windows, macOS, Android and ChromeOS) to guard against zero-day threats and APT attacks with unmatched accuracy.

“Whether it's typical ransomware or not, attack vectors are constantly changing, and without the correct tools to tell you when a malicious attack will occur, deep learning-based cybersecurity is the only answer to best protect against the known and unknown,” said Guy Caspi, CEO and co-founder of Deep Instinct. “The results speak for themselves and are indicative of our mission and commitment to keep customers safe from a multitude of cyber threats.”

The test comprised four main categories of attack: known, public malware campaigns; script-based targeted attacks, e.g. file-less, designed to avoid interacting with the hard disk of target systems; targeted attacks based on macros and vulnerabilities in Microsoft Office file-formats, e.g. ‘client-side attacks, and shellcode injection attacks designed to inject malicious code into legitimate software.

To effectively test D-Client software, SE Labs collected malware from a range of well-known breaches, including attacks from APT28 (Fancy Bear) that originally targeted the U.S. presidential election of 2016; APT29 (Cozy Bear) which was believed to be behind the compromise of the U.S. Democratic National Committee in 2015 and a banking Trojan designed to steal personal details – identified by the U.S. Department of Homeland Security and many others. The samples that were tested were new variants of those campaigns, which were never available in the wild before.

In addition to the known ‘public’ threats, SE Labs testers also generated a range of advanced targeted attacks using known malicious techniques to create new, unknown files. These included malicious Microsoft Office and JavaScript files, which were included to explore whether D-Client could handle malware of which it lacked prior knowledge and file-less attacks. Not only did D-Client detect all the public or “known” attacks, it successfully protected against every one of the new Microsoft Office-related attacks launched. It also went a step further to protect systems from any ill-effects, such as infection from ransomware and theft or data destruction.

“The number of modern threats has grown significantly over the years, just as their behavior has also changed, leveraging automation and AI-like techniques for maximizing their impact and velocity”, said Fernando Montenegro, a senior industry analyst at 451 Research. “That said, the same type of machine learning/AI techniques can and have been employed by defenders with great success. As organizations look at their options for building security defenses, test results by external labs are one of the significant signals to consider in their selection process.”

Download the full SE Lab report  here.

About Deep Instinct
Deep Instinct is the first company to apply deep learning to cybersecurity. Deep learning is inspired by the brain’s ability to learn. Once a brain learns to identify an object, its identification becomes second nature. Similarly, as Deep Instinct’s artificial deep neural network brain learns to prevent any type of cyber threat, its prediction capabilities become instinctive. As a result, any kind of malware, known and new, first-seen malware, zero-days, ransomware and APT attacks from any kind are predicted and prevented in zero-time with unmatched accuracy and speed anywhere in the enterprise – Network, EPP, Mobile - enabling a multi layered protection. To learn more, visit: https://www.deepinstinct.com

Media Contact:
Jaime Tero
Allison+Partners
DeepInstinctUS@allisonpr.com