Israeli AI cybersecurity lab Irregular is raising funds at a valuation of $1.5 billion, in a financing round led by Joshua Kushner’s Thrive Capital and Greenoaks Capital, "Globes" has learned. Irregular has been in the center of a storm in recent months over hacking by its customers Anthropic, Meta, OpenAI and Google, according to reports.
It seems that the series of reports on the language models of Anthropic, OpenAI, Google and Meta "breaking out" of Irregular’s ??testing environment have not actually harmed the company. The reports have generated a buzz around the business.
In an interview with "Globes," earlier this month cofounder and CTO Omer Nevo, acknowledged that the negative publicity had not caused any damage. "We have deepened our work with the leading labs, and Google and OpenAI have become our clients," he said. "Today, I can say that we are enhancing the models' defensive capabilities and assisting in their training to make them safer. We work not only with companies but also with governments to ensure human control over AI models when they behave unpredictably. Over the past year, our volume of work with the major labs has expanded, and the company itself has grown. We now have 50 employees."
The company did not respond to inquiries from "Globes" regarding the new financing round. As the round has not yet been finalized, the final amount could change, and new investors might still participate.
Irregular, founded by entrepreneurs CEO Dan Lahav and Nevo, provides AI giants with a software testing environment that subjects language models to extreme scenarios, helping to assess their safety and stability. In other words, it allows the models to "run wild" within its self-contained environment, technically known as a "sandbox," to test for the risks and vulnerabilities they might harbor.
Just over a year ago, Lahav and Nevo announced an $80 million funding round led by Sequoia Capital and with participation by Redpoint Ventures, Assaf Rappaport, and former NBA basketball player Omri Casspi, to found the AI cybersecurity lab Irregular.
Today, the company serves Silicon Valley’s AI giants. However, between July and September, these companies successively announced that language models they had developed had inadvertently escaped Irregular’s ??testing environment and leaked onto the internet.
Irregular accepted some of the responsibility for the breach but explained that it stemmed from an incorrect "internet exit" configuration on its part, as well as a specific system setup in its customers' software, which disrupted communication between the companies.
Published by Globes, Israel business news - en.globes.co.il - on September 23, 2026.
© Copyright of Globes Publisher Itonut (1983) Ltd., 2026.