Ghost Security reinvents app security with unattended machine learning

Software applications are at the heart of organizations of all sizes in all industries. Using APIs and microservices creates an ecosystem between users and the information they need. Because of this, there has been an exponential expansion in the development and use of applications and APIs – often leaving them unaccounted for and unsecured, according to Ghost Securityan application security company.

The industry is struggling to resolve the security risks facing cloud applications. Several subcategories of products attempt to support that goal, from cloud security attitude management (CSPM) to identity access management (IAM), web application firewall (WAF), data loss prevention (DAP), runtime security tools, static analytics, and dynamic analytics.

However, despite all these point products, compromises in applications are increasing, the company said.

Coming to AI with unattended machine learning

Ghost Security, which has emerged from stealth mode today, says it is taking a different approach and using machine learning (ML) as a core component of its platform. With this technology, security professionals can distinguish normal behavior from abnormal behavior and detect when something abnormal happens. “The great thing about this is that you have the ability to detect attacks that no one has seen before,” Ghost co-founder and CEO Greg Martin told VentureBeat.

The company claims its platform will help technology leaders continue rapid application development without disrupting existing processes, and provide detection and response teams with comprehensive and automated application protection.

“We’re trying to build a lot of innovation into creating defenses for not just today’s applications, but for the next decade or two,” Martin said. “In practice, that means using technology that wasn’t available 10 or 12 years ago,” such as machine learning, artificial intelligence (AI), and horizontal cloud scaling systems.

Many app security products use supervised machine learning, where algorithms are trained using good and bad data so the system understands what to look for, Martin said. But Ghost uses an unsupervised machine learning approach, “where you don’t have to feed it data; it’s learning in a different way,” he explained.

Another differentiator is “we design our software in a way that is compatible with anything” [cloud provider] the client uses,” said Martin. “So if [they use] Google or Amazon Web Services or Microsoft Azure – or something completely different – we’re going to build compatibility for every customer.”

That includes customers with on-premises data centers, Martin added.

A better approach is needed to secure assets

“The exciting thing about the Ghost platform is that it removes the complex and intrusive processes needed to protect applications and APIs, making this kind of technology more accessible to organizations around the world,” said Florian Leibert, general partner and co-founder at 468 Capital, in a statement. “They’re building a solution that scales without impacting productivity and leverages the power of machine learning in a way that identifies unknown vulnerabilities and stops more threats.”

Ghost Security is backed by a $15 million joint investment from 468 Capital, DNX Ventures and Munich Re Ventures. Announcing the financing, the company said it will use this inflow of capital to continue to focus on building “a world-class team with the experience and passion needed to develop disruptive technologies.”

“The rapid adoption of applications, APIs and microservices represents great growth potential for businesses, but also introduces many new attack surfaces,” said Hiro Rio Maeda, managing partner at DNX Ventures, in a statement. “A better approach is needed to secure these assets, and Ghost is well positioned to meet that challenge.”

Ghost competes with companies including: Imperva, F5 and Akamaisaid Martin. “The space we disrupt has traditionally been referred to as ‘web application firewalls,’ but the tools are so simplistic that we think with what we’re doing, we won’t be the only ones to jump in and do this,” Martin said.