REVIEW 4 cited by
Low-Cost and Comprehensive Non-textual Input Fuzzing with LLM-Synthesized Input Generators
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a given input format. Nevertheless, LLMs are often incapable or too costly to generate non-textual outputs, such as images, videos, and PDF files. This limitation hinders the application of LLMs in grammar-aware fuzzing. We present a novel approach to enabling grammar-aware fuzzing over non-textual inputs. We employ LLMs to synthesize and also mutate input generators, in the form of Python scripts, that generate data conforming to the grammar of a given input format. Then, non-textual data yielded by the input generators are further mutated by traditional fuzzers (AFL++) to explore the software input space effectively. Our approach, namely G2FUZZ, features a hybrid strategy that combines a holistic search driven by LLMs and a local search driven by industrial quality fuzzers. Two key advantages are: (1) LLMs are good at synthesizing and mutating input generators and enabling jumping out of local optima, thus achieving a synergistic effect when combined with mutation-based fuzzers; (2) LLMs are less frequently invoked unless really needed, thus significantly reducing the cost of LLM usage. We have evaluated G2FUZZ on a variety of input formats, including TIFF images, MP4 audios, and PDF files. The results show that G2FUZZ outperforms SOTA tools such as AFL++, Fuzztruction, and FormatFuzzer in terms of code coverage and bug finding across most programs tested on three platforms: UNIFUZZ, FuzzBench, and MAGMA.
Forward citations
Cited by 4 Pith papers
-
RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry
On a 160,000-file industrial C++ codebase, BM25-based retrieval-augmented generation outperformed fine-tuning for line-level code completion, and combining RAG with fine-tuning further improved accuracy.
-
ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference
ZTaint-Havoc piggybacks black-box taint inference onto AFL++ havoc mutations, then biases later mutations toward the inferred hot bytes, raising average edge coverage by 2.97% on FuzzBench and 6.12% on UniBench in 24-...
-
Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models
Reasoning depth in code LLMs should be managed as a controllable resource across synthetic data generation, benchmarking, and deployment, rather than left implicit.
-
Position Paper: Programming Language Techniques for Bridging LLM Code Generation Semantic Gaps
A position paper arguing that PL techniques, especially formal verification and structure-aware representations, should be deeply integrated into LLM code generation.
Discussion (0). Sign in to comment.