Inspiration

Agentic commerce is the future. AI agents will soon autonomously buy our groceries, pay our bills, and manage our subscriptions. But a fundamental trust problem exists: How does a payment processor know the AI didn't hallucinate the price, or worse, get hijacked by a malicious prompt injection to drain a user's bank account?

We built Proof of Inference to solve this. We don't just trust the AI; we mathematically enforce its constraints.

What it does

Proof of Inference is a production-grade, zero-trust architecture that sits between a local AI and the PayPal API.

  1. Local AI Engine: Uses Qwen 2.5 (7B) with GBNF grammar to guarantee 100% strict JSON output (no hallucinations).
  2. Cryptographic Lifecycle: The backend wraps the AI's JSON in a lifecycle envelope (containing a tx_id, nonce, and 60-second expiry) and signs it using Ed25519.
  3. Deterministic Risk Engine: A backend policy engine calculates a Trust Score. It blocks suspicious prompts, high-value anomalies, and unknown merchants.
  4. Dead Man's Switch: The user has 60 seconds to authorize or revoke the exact signed transaction.
  5. Atomic State Machine: Uses SQLite to prevent race conditions (e.g., clicking "Abort" while the backend is calling PayPal).
  6. Crash-Safe Recovery: If the backend crashes mid-capture, a startup daemon reconciles the transaction with PayPal to prevent double-charging.

The Winning Demo: LLM Hijack Defense

We included an Adversarial Lab in the UI. A user can inject a malicious <system_override> into a product description. The local Qwen 2.5 model actually gets hijacked and attempts to generate a $999 purchase for a $30 item.

However, our independent backend policy engine catches the anomaly. The Trust Score spikes to 90/100, and PayPal Capture API Calls remain at 0. The AI is compromised, but the architecture holds. No money moves.

How we built it

  • AI Engine: Ollama, Qwen 2.5, GBNF Grammar
  • Cryptography: PyNaCl (Ed25519 signatures)
  • Database: SQLite (Atomic state transitions)
  • Payments: PayPal Orders v2 API (Idempotency, Create -> Capture flow)
  • UI: Streamlit (6-tab enterprise SOC dashboard)

Accomplishments that we're proud of

  • Implementing an atomic SQLite state machine that mathematically prevents race conditions between ABORT and CAPTURE.
  • Writing a startup reconciliation daemon that guarantees no double-charging after a backend crash.
  • Building a prompt injection demo that proves the AI can be fully compromised without resulting in financial loss.

What's next for Proof of Inference

  • Migrating the Ed25519 private keys from local memory to a secure AWS KMS or HSM.
  • Implementing real PayPal Webhooks with signature verification for production reconciliation.
  • Expanding the Risk Engine with real-time behavioral anomaly detection.

Built With

Share this project:

Updates

Submission history