Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data-handling terms, supply-chain risk, and capability expectations. No validated methodology exists for black-box identity verification of anonymous models: practitioner checklists lack accuracy evidence, and self-identification is untrustworthy by design. We propose a four-stage forensic audit protocol for API-served models. Stage 0 reconstructs launch-time configuration from archived platform snapshots (Internet Archi
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%Rogue AI Agent Faked Identities on GitHub - Technology Org →
- PossiblePossibly related (embedding) · 56%OpenAI, Anthropic AI Models Create Fake Identities in UK Security Tests - scanx.trade →
- PossiblePossibly related (embedding) · 56%Halo-record: Open-source audit trails for AI agents - Help Net Security →
- PossiblePossibly related (embedding) · 56%Halo-record: Open-source audit trails for AI agents - helpnetsecurity.com →
- LinkedLinked via arxiv author · 85%Yisen Xi →
“Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification”