At Irregular, we build evaluations that measure how frontier models perform in realistic offensive security operations. Google DeepMind used CyScenarioBench, our benchmark for multi-stage offensive ...

Sign up for our newsletter and get notified of irregular updates ...

We are happy to share that we have started working with Reflection. At Irregular, we build evaluations that measure how frontier models perform in realistic offensive security operations. As part of ...

Irregular has been named to the Disruptors 60 Class of 2026, a list curated by Greenfield Partners and unveiled at TechCrunch Disrupt, spotlighting 60 startups shaping the future of AI. Irregular is ...

We are building the world’s first frontier security lab to solve the most critical AI security challenges and architect the next generation of defenses. Our team is small but talent-dense: AI ...

LLM-generated passwords appear strong, but are fundamentally insecure. Testing across GPT, Claude, and Gemini revealed highly predictable patterns: repeated passwords across runs, skewed character ...

We studied a self-hosted system in which the same open-weights model powered both a coding agent and an AI application that the coding agent was asked to maintain. This architecture is particularly ...

AI agents deployed for routine enterprise tasks are autonomously hacking the systems they operate in. No one asked them to. No adversarial prompting was involved. The agents independently discovered ...

Existing cybersecurity benchmarks are gradually becoming saturated across frontier models, offering diminishing insight into real-world risk. As LLMs begin to influence security incidents in the wild, ...

Autonomous AI agents are increasingly being deployed for offensive security tasks. These models can scan codebases in seconds, identify misconfigurations at machine speed, and execute tactical exploit ...

At Irregular, we rigorously test cutting-edge models against real offensive security challenges and derive vulnerability, exploitation, and orchestration metrics to assess their practical capabilities ...

At Irregular, we rigorously test cutting-edge models against real offensive security challenges and derive vulnerability, exploitation, and orchestration metrics to assess their practical capabilities ...