Map / Model Security / Starseer
Starseer
starseer.ai ↗ · LinkedIn ↗ · Open on the map
Model SecurityAI Endpoint SecurityRuntime & Guardrails
Capabilities
AI-Verify (pre-deployment model validation via interpretability — detects backdoors, hidden capabilities, misaligned representations); AI-EDR (versioned behavioral detections running continuously across AI endpoints); AI-SIR (intelligent routing across model fleets by policy, cost, compliance with containment).
Sensors / integration
Mechanistic interpretability / activation analysis of model internals at inference; LLM gateway routing layer across model fleets.
Protections
Block/contain on detection of backdoors, covert capabilities, misaligned behavior; policy/compliance-driven request routing.
Differentiator
Inspects model internals via interpretability rather than only outputs — surfaces hidden threats invisible to output monitoring. Advisors Rob Joyce (ex-NSA), Gary McGraw (BIML); partners SCYTHE, OWASP GenAI, MITRE ATLAS.
Team & funding
- Founders
- Tim Schulz, Carl Hurd
- Total raised
- $2M
- Investors
- Gula Tech Adventures
Other Model Security companies
ActiveFence · Advai · Adversa AI · AI Aramid · Alice · AptaSentry · Arize AI · Attestable · Bosch AIShield · Citadel AI · Cranium AI · DataKrypto · See all →
Last updated · Get the “Listed on” badge