LATIDIA · Ciberseguridad

The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics

arXiv: 2609.14098v1Tipo de anuncio: nuevo Resumen: Los modelos de lenguaje grandes se utilizan cada vez más en las investigaciones forenses de blockchain para interpretar el código de bytes de contratos inteligentes no verificados. Su robustez no ha sido sistemática

La noticia

arXiv:2609.14098v1 Announce Type: new Abstract: Large language models are increasingly used in blockchain forensic investigations to interpret unverified smart contract bytecode. Their robustness has not been systematically tested against contracts adversarially designed to mislead analysis. We evaluate 22 frontier models on 13 purpose-built contracts (9 deception vectors, 4 controls) across six prompt strategies, yielding 8,528 analyzable non-refusal runs against contracts with EVM-verified ground truth. A calibrated LLM-as-judge pipeline, supported by two judge-independent metrics and 50 human gold-standard labels, shows that adversarial deception reduces drain detection by 20.0 percentage points (95% CI: [17.2, 22.8]) relative to functionally matched controls. Structural camouflage via multi-hop call chains, XOR-masked selectors, and storage-loaded drain parameters