Sophos launches open AI developments to fight cyberattacks

Cybersecurity company Sophos is announcing four new open artificial intelligence developments with the aim of improving defenses and making the use of AI in cybersecurity more transparent.

Although in other industries it's become common to share AI methodologies and findings, cybersecurity has lagged which doesn't help understanding of how AI can protect against cyberthreats.

Sophos and its team of SophosAI data scientists are hoping to drive a change toward more openness, so that IT managers, security analysts, CFOs, CEOs, and others making security buying or management decisions, can discuss and assess AI benefits from a level and well-informed playing field.

"With SophosAI's new initiative to open its research, we can help influence how AI is positioned and discussed in cybersecurity moving forward. Today's cacophony of opaque or guarded claims about the capabilities or efficacy of AI in solutions makes it difficult to impossible for buyers to understand or validate these claims. This leads to buyer skepticism, creating headwinds to future progress at the very moment we're starting to see great breakthroughs," says Joe Levy, chief technology officer at Sophos. "Correcting this through external mechanisms like standards or regulation won't happen quickly enough. Instead, it requires a grassroots effort and self-policing within our community to produce a set of practices and language that will advance the industry in a disruptive, open and transparent manner."

The developments are in four areas. First is SOREL-20M, a joint project between SophosAI and ReversingLabs, creating a dataset containing metadata, labels and features for 20 million Windows Portable Executable files (PE). It includes 10 million disarmed malware samples available for download for the purpose of research on feature extraction to accelerate industry-wide improvements in security.

Impersonation Protection is designed to protect against email spearphishing attacks by comparing the display name of inbound emails against high level executive titles -- those most likely to be spoofed in a spearphishing attack, such as a CEO, CFO or president -- that are unique to specific organizations and flagging these messages when they appear suspicious.

There's a set of epidemiology-inspired statistical models for estimating the prevalence of malware infections in total. This enables Sophos to estimate -- and in turn have a better chance to find -- the needles in a PE file haystack. This has been made publicly available to help to determine malicious 'dark matter', malware that might be missed or wrongly classified.

Finally there's a new method for automatic signature generation, called YaraML, that significantly differs from previous options by taking an AI based approach to the problem.

You can read more about these developments on the Sophos blog.

Image Credit: agsandrew / depositphotos.com