// LABS · RESEARCH FIELDS

The fields we research
and build.

We turn problems met in the field into research, building the tools, data, and methods to stay ahead of the next threat. Questions raised by our services become Labs research, and the results flow back to the field.

// 01 · RESEARCH FIELDS

Five threads, all starting in the field.

The fields are connected — a finding in one becomes tools, data, and playbooks that speed the research in another.

AI, LLM & agent security

AI, LLM & Agent Security

The attack surface of security models and agent services, and defenses against prompt attacks, data leakage, and misuse.

Human–AI security operations

Human–AI Security Operations

We design and verify human–agent workflows governed by roles, permissions, approvals, and verification.

Industrial & cyber-physical

Industrial & Cyber-Physical

Vulnerability testing and zero-day discovery for OT, ICS, IoT, firmware, and robots — down to physical safety impact.

Offensive & defensive knowledge

Offensive & Defensive Knowledge

We structure real attack and defense techniques into methods, playbooks, and industry baselines.

Agent evaluation & benchmarks

Agent Evaluation & Benchmarks

We build the criteria and datasets to evaluate an AI agent's capability and safety on security work.

// 02 · COLLABORATE

Have a problem worth researching together?

We welcome research collaboration, technical exchange, and talent inquiries.