Irregular
Last verified 2026-05-22. JSON
The funding figures on this page are attributed, not sourced: a publisher is on record but no document URL is. How we mark provenance.
| Total raised | $80.0Mattributed |
|---|---|
| Latest round | series-b, $80.0M, 2025-09-17attributed |
| Founded | 2023 |
| Headquarters | United States, US |
| Industry | cybersecurity |
| Stage | series-b+ |
| Website | irregular.com |
Irregular is a security research lab that stress-tests frontier AI models against offensive-security benchmarks to surface safety and misuse risks. It works with the major AI labs releasing those models, publishing evaluations of systems like GPT-5.5 and Meta Muse Spark. The lab focuses purely on frontier-AI risk, not general cybersecurity.
Funding rounds
| Date | Round | Amount | Lead |
|---|---|---|---|
| 2025-09-17 | series-b | $80.0M | sequoia |
Detected tech stack
Google Analytics, Google Tag Manager, Framer Sites, DoubleClick Floodlight, Vercel Speed Insights, WordPress, React 16.13.1, PHP, MySQL
Provenance
| Fact | Status | Basis |
|---|---|---|
| Series B, $80.0M | attributed | techcrunch named as publisher. No document URL on file. |
| Total raised $80.0M | attributed | techcrunch named as publisher. No document URL on file. |
| Company existence | self-reported | irregular.com, read 2026-05-22 |
| Description | self-reported | irregular.com, read 2026-05-22 |
Nothing on this page is sourced yet. A sourced fact links to a document that states it.
Change history
No change recorded since records began on 2026-09-24.