How discoveries become detections
Discover
Labs researchers find new AI vulnerability
Analyse
Characterise attack, map to MITRE ATLAS
Publish
Advisory + CVE + YAML detection signatures
Deploy
Signatures ship to Gateway + Sensor automatically
Comprehensive threat coverage
Adversarial ML
Prompt injection, jailbreaking, role hijacking, instruction override, and model behaviour manipulation techniques.
AI Agent Security
Tool-call abuse, MCP server exploitation, agent manipulation, multi-turn attacks, and autonomous system threats.
Model Supply Chain
Training data poisoning, model backdoors, weight manipulation, and supply chain integrity threats.
Prompt Injection Taxonomy
Systematic classification of injection techniques, encoding tricks, evasion patterns, and context manipulation methods.
Published research
Security Advisories
CVE-tracked vulnerability disclosures with MITRE ATLAS mapping and detection signatures.
Threat Intelligence
Data-driven threat landscape reports with trend analysis, emerging threats, and actionable recommendations.
Detection Signatures
Open YAML-based detection rules, continuously updated from research findings.
Cold Validation
Independent AI change assurance for high-risk agent workflows. Separation of duties, release governance, and retained audit evidence.
Enterprise Research Partnerships
RAXE Labs discovers threats. RAXE Intelligence turns them into enforceable protection. Partner with us to stay ahead.