MoCQ combines LLMs with symbolic validation to generate vulnerability patterns for static analysis, matching expert performance on 12 types across four languages and finding 25 new real-world vulnerabilities.
Neves, and Miguel Correia
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns
MoCQ combines LLMs with symbolic validation to generate vulnerability patterns for static analysis, matching expert performance on 12 types across four languages and finding 25 new real-world vulnerabilities.