Skip to content
Preprint

When Verified Source Becomes Attack Input: Defending Smart Contracts Against LLM-Based Vulnerability Scanning

Aug 2026 · 0 citations · 38 references
Computer Science

TL;DR

DeLLMGuard is proposed, a smart contract deployment framework that defends against malicious LLM-based vulnerability scanning while preserving public source disclosure and authorized auditing and outperforms the closed-source bytecode baseline on the primary non-proxy set.

Abstract

Smart contracts are financial programs deployed on blockchains to manage digital assets. To build trust with users and investors, smart contract projects typically publish their source code on blockchain explorers and verify it against the deployed bytecode, making the on-chain program accessible through a human-readable implementation. However, LLM agents are changing the threat model of this disclosure mechanism. By leveraging publicly disclosed source code, recent agent workflows make it increasingly practical to scan contract vulnerabilities for exploits at large scale. In this paper, we propose DeLLMGuard, a smart contract deployment framework that defends against malicious LLM-based vulnerability scanning while preserving public source disclosure and authorized auditing. DeLLMGuard can separate disclosed source code from runtime execution through multiple contract addresses in a real-world blockchain environment. LLM agents must therefore recover additional proxy, delegate, and factory relations before vulnerability analysis. A built-in Verification Layer checks deployment relations, runtime bytecode, source code, and state changes to ensure that the transformation preserves the original business implementation. We evaluate DeLLMGuard on 387 real-world vulnerable contracts with three LLM agents in an environment derived from SCONE-bench. DeLLMGuard reduces overall root-cause correctness from 23.5% to 6.6% and outperforms the closed-source bytecode baseline on the primary non-proxy set. Trace and ablation analyses further show that agents often recover downstream contracts but still fail to identify the vulnerability, indicating that cross-contract recovery remains a major challenge for automated LLM scanning.

View source

Similar papers

Review Open access 2026

SVACS: Smart Contract Vulnerability Analysis via Control Flow Semantics

This paper proposes SVACS, a bytecode-based analysis framework to identify multiple co-existing vulnerabilities based on SWC registry to align with industry-standard security guidelines and assist security reviewers to ensure smart contract security.

Ankur Jain, Abhishar Anand, S. Tripathy · 0 citations
Preprint Sep 2026

Function Name Is All You Need to Detect Blockchain Application Attacks

It is argued that function name sequences suffice to capture the high-level semantics of a transaction, and hence can be used to detect blockchain application attacks, and TxLucent, an automated framework to detect blockchain application attacks by extracting application semantics from transaction call traces is propos...

Rui Xi, Ze-Hua Wang, Karthik Pattabiraman · 0 citations
Open access Oct 2026

Blockchain-Based Smart Contract Escrow for Secure and Transparent Property Transactions

Background: Conventional property escrow depends on intermediaries and sequential verification, which can limit transaction visibility and create opportunities for delays, inconsistent records, and disputes. Blockchain-based smart contracts provide an auditable execution environment in which predefined conditions can a...

Omega Joel Patria Moata, Febi Elvira Messe, Fiktor Imanuel Tanesab · 0 citations

Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains

A blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also securing the agentic AI components responsible for monitoring it, and a generalisable architecture to incorporate the agentic AI into the modern software supply chain security.

Toqeer Ali Syed, A. Khan · 1 citation
Review Open access Sep 2026

Security of The Model Context Protocol Ecosystem: Emerging Threats, Empirical Attack Evidence, Trust and Authorization Failures, Supply-Chain Risks, And Defensive Strategies

The review concludes that MCP security should move from prompt-centric protection toward policy-centric, lifecycle based, and risk-adaptive security, supported by interoperable standards for cryptographic identity, capability attestation, provenance, benchmarking, data-flow enforcement, and security evaluation.

Khalid D. Muhammed, David Chinonso Anih · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.