Boosting Skeleton-Driven SMT Solver Fuzzing by Leveraging LLM to Produce Formula Generators
By: Maolin Sun, Yibiao Yang, Yuming Zhou
Potential Business Impact:
Finds hidden bugs in computer code faster.
Satisfiability Modulo Theory (SMT) solvers are foundational to modern systems and programming languages research, providing the foundation for tasks like symbolic execution and automated verification. Because these solvers sit on the critical path, their correctness is essential, and high-quality test formulas are key to uncovering bugs. However, while prior testing techniques performed well on earlier solver versions, they struggle to keep pace with rapidly evolving features. Recent approaches based on Large Language Models (LLMs) show promise in exploring advanced solver capabilities, but two obstacles remain: nearly half of the generated formulas are syntactically invalid, and iterative interactions with the LLMs introduce substantial computational overhead. In this study, we present Chimera, a novel LLM-assisted fuzzing framework that addresses both issues by shifting from direct formula generation to the synthesis of reusable term (i.e., logical expression) generators. Particularly, Chimera uses LLMs to (1) automatically extract context-free grammars (CFGs) for SMT theories, including solver-specific extensions, from documentation, and (2) synthesize composable Boolean term generators that adhere to these grammars. During fuzzing, Chimera populates structural skeletons derived from existing formulas with the terms iteratively produced by the LLM-synthesized generators. This design ensures syntactic validity while promoting semantic diversity. Notably, Chimera requires only one-time LLM interaction investment, dramatically reducing runtime cost. We evaluated Chimera on two leading SMT solvers: Z3 and cvc5. Our experiments show that Chimera has identified 43 confirmed bugs, 40 of which have already been fixed by developers.
Similar Papers
LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models
Software Engineering
Finds hidden bugs in new computer code.
InvBench: Can LLMs Accelerate Program Verification with Invariant Synthesis?
Programming Languages
Helps computers find bugs in code faster.
ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space
Cryptography and Security
Finds software bugs automatically.