SDLLMFuzz combines LLM-based generation of syntactically valid inputs with a dynamic-static feedback loop from crash artifacts to improve bug discovery and time-to-bug on structured-input programs compared to traditional and LLM-assisted fuzzers.
Fuzzing: A survey for roadmap
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SDLLMFuzz: Dynamic-static LLM-assisted greybox fuzzing for structured input programs
SDLLMFuzz combines LLM-based generation of syntactically valid inputs with a dynamic-static feedback loop from crash artifacts to improve bug discovery and time-to-bug on structured-input programs compared to traditional and LLM-assisted fuzzers.