Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework

Harshil Parmar, Pushti Vyas, Prayers Khristi, Priyank Panchal

TL;DR

Zer0n tackles the trust gap in AI-driven vulnerability discovery by binding LLM-based reasoning to an immutable blockchain ledger. It combines Gemini 2.0 Pro for vulnerability reasoning with an Avalanche C-Chain based integrity layer that records cryptographic hashes $h = H(R)$ of analyses, enabling verifiable audit trails while keeping computation off-chain for speed. Empirical results on 500 endpoints show a precision of $78\%$, recall of $82\%$, and an F1 of $80\%$, with an overhead of $22.9\%$, indicating practical feasibility for security workflows. Overall, Zer0n demonstrates that a hybrid architecture can provide both rapid vulnerability analysis and mathematically verifiable provenance, paving the way for trustable AI-assisted cybersecurity research.

Abstract

As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that anchors the reasoning capabilities of Large Language Models (LLMs) to the immutable audit trails of blockchain technology. Specifically, we integrate Gemini 2.0 Pro for logic-based vulnerability detection with the Avalanche C-Chain for tamper-evident artifact logging. Unlike fully decentralized solutions that suffer from high latency, Zer0n employs a hybrid architecture: execution remains off-chain for performance, while integrity proofs are finalized on-chain. Our evaluation on a dataset of 500 endpoints reveals that this approach achieves 80% detection accuracy with only a marginal 22.9% overhead, effectively demonstrating that decentralized integrity can coexist with high-speed security workflows.

Zer0n: An AI-Assisted Vulnerability Discovery and Blockchain-Backed Integrity Framework

TL;DR

Zer0n tackles the trust gap in AI-driven vulnerability discovery by binding LLM-based reasoning to an immutable blockchain ledger. It combines Gemini 2.0 Pro for vulnerability reasoning with an Avalanche C-Chain based integrity layer that records cryptographic hashes of analyses, enabling verifiable audit trails while keeping computation off-chain for speed. Empirical results on 500 endpoints show a precision of , recall of , and an F1 of , with an overhead of , indicating practical feasibility for security workflows. Overall, Zer0n demonstrates that a hybrid architecture can provide both rapid vulnerability analysis and mathematically verifiable provenance, paving the way for trustable AI-assisted cybersecurity research.

Abstract

As vulnerability research increasingly adopts generative AI, a critical reliance on opaque model outputs has emerged, creating a "trust gap" in security automation. We address this by introducing Zer0n, a framework that anchors the reasoning capabilities of Large Language Models (LLMs) to the immutable audit trails of blockchain technology. Specifically, we integrate Gemini 2.0 Pro for logic-based vulnerability detection with the Avalanche C-Chain for tamper-evident artifact logging. Unlike fully decentralized solutions that suffer from high latency, Zer0n employs a hybrid architecture: execution remains off-chain for performance, while integrity proofs are finalized on-chain. Our evaluation on a dataset of 500 endpoints reveals that this approach achieves 80% detection accuracy with only a marginal 22.9% overhead, effectively demonstrating that decentralized integrity can coexist with high-speed security workflows.
Paper Structure (23 sections, 1 equation, 3 figures, 7 tables, 1 algorithm)

This paper contains 23 sections, 1 equation, 3 figures, 7 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. AI-Assisted Vulnerability Discovery
  4. Evolution of Smart Contract Analysis
  5. Generative AI Security Risks
  6. Blockchain and Cybersecurity
  7. Standards and Threat Landscape
  8. Comparative Analysis
  9. System Architecture
  10. Blockchain-Backed Integrity & Subscription
  11. Workflow Coordination
  12. Implementation
  13. Evaluation
  14. Experimental Setup
  15. Evaluation Metrics
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Zer0n system architecture illustrating trust boundaries, adversarial environment, and blockchain-backed integrity logging.
  • Figure 2: Verification flow in Zer0n. A vulnerability report is hashed and recorded on the blockchain. Any post-analysis modification results in a hash mismatch during verification, enabling tamper detection.
  • Figure 3: Sequence Diagram illustrating the interaction flow associated with a vulnerability scan. Time flows downwards. The Node.js backend acts as a bridge, preserving the asynchrony of the analysis while ensuring atomic logging on the Avalanche blockchain.