RAXE Labs

Security research

Original AI security research from the team that builds RAXE. Every vulnerability we find becomes a detection signature. Every pattern we document makes the platform stronger.

Security Advisories Threat Intelligence
Research Mission
Discover AI threats before attackers exploit them. Publish findings openly. Turn every discovery into enforceable protection that ships automatically to RAXE Gateway and Sensor.
4 Research Streams

Where we focus

Research organized into four streams, each targeting a distinct category of AI security threats.

S1

Adversarial ML

Jailbreaking, prompt injection, model behaviour manipulation

S2

Agent Security

Tool-call abuse, MCP exploits, agent manipulation

S3

Supply Chain

Framework vulnerabilities, model registry threats

S4

Prompt Injection

Injection taxonomy, encoding tricks, evasion patterns

Open Detection Content

515+ YAML-based signatures

Every research finding produces detection signatures. Open, auditable, mapped to MITRE ATLAS, and continuously updated.

515+
Detection Signatures
38
Published Advisories
Monthly
Threat Reports
Coming Soon

Upcoming publications

Q2 2026

MCP Server Attack Surface Analysis

Comprehensive analysis of Model Context Protocol server vulnerabilities, including tool-call injection, permission escalation, and cross-server data exfiltration.

Q2 2026

AI Agent Exploitation Taxonomy

A systematic classification of attack techniques targeting autonomous AI agents, including multi-turn manipulation, sandbox escapes, and inter-agent trust exploitation.

Q3 2026

Prompt Injection Evasion Benchmark

Benchmarking prompt injection detection systems against adversarial evasion techniques, including encoding, obfuscation, and multi-language attacks.

Q3 2026

LLM Supply Chain Risk Report

Analysis of dependency risks in the AI/ML ecosystem, covering model registries, framework vulnerabilities, and training pipeline integrity.

Stay ahead of AI threats

Our research feeds directly into RAXE platform detections. Deploy the platform to turn every finding into automated protection.

Request a Demo Talk to an Engineer
RAXE Labs → RAXE Intelligence →