Oct 2026· Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering· 1 citation· 63 references
TL;DR
This paper presents hybrid generator space fuzzing, a method that combines the strengths of hybrid fuzzing and generator-based fuzzing to improve the syntactic validity and semantic diversity of test inputs and implements GenEvo, an LLM-driven hybrid generator space fuzzer.
Abstract
The core challenge of fuzzing is to consistently generate test inputs that are both syntactically valid and semantically diverse. However, mutation-based coverage-guided fuzzing often struggles to achieve this, especially for highly structured formats. Two lines of work have emerged to address this challenge: (1) hybrid fuzzing uses constraint solving to drive execution toward hard-to-cover program states to increase semantic diversity, and (2) generator-based fuzzing relies on predefined or synthesized input-generation programs to ensure syntactic validity. Both approaches, however, have significant limitations. (1) In hybrid fuzzing, solved inputs are fed back into the fuzzing queue for byte-level mutation, which often breaks syntactic structure (e.g., checksums and cross-field dependencies) and causes early rejection. (2) In generator-based fuzzing, semantic diversity is constrained by static generators based on domain knowledge; although recent work introduces generator mutations, they remain blind and therefore have limited adaptability to the target program’s logic. In this paper, we present hybrid generator space fuzzing, a method that combines the strengths of hybrid fuzzing and generator-based fuzzing to improve the syntactic validity and semantic diversity of test inputs. The key idea is to treat input generators, rather than test inputs, as the unit of targeted solving, and to use the LLM as constraint solver to derive new generators. This design offers two benefits. First, compared with hybrid fuzzing, it preserves syntactic validity because inputs are generated directly from evolving generators rather than through byte-level mutation of solved seeds. Second, compared with generator-based fuzzing, it overcomes the limitations of static generators and blind generator mutations, enabling the fuzzer to adapt to target program logic and explore a broader semantic space. Building on this concept, we implement GenEvo, an LLM-driven hybrid generator space fuzzer. Our evaluation on a large set of real-world programs shows that GenEvo, using a locally deployed medium-sized LLM, significantly outperforms competitive baselines (including general-purpose, hybrid, structure-aware, and LLM-assisted fuzzers) in both branch coverage (with an average improvement of 98.3%) and vulnerability discovery. Furthermore, GenEvo has discovered 25 previously unknown vulnerabilities in these extensively-tested programs.
Modern generator-based fuzzing techniques combine lightweight input generators with coverage-guided mutation as a method of exploring deep execution paths in a target program. A complementary approach in prior research focuses on creating highly customized, domain-specific generators that encode structural and semantic...
Vasudev Vikram, Rohan Padhye· Proceedings of the 41st IEEE...· 2 citations
Repair-driven greybox fuzzing is presented, a new approach to greybox fuzzing that combines the strengths of unstructured, byte-level input mutation and grammar-guided input generation that promises to improve bug-finding ability for systems under test such as programming language interpreters that consume highly struc...
Bachir Bendrissou, Alastair F. Donaldson, Cristian Cadar· Proceedings of the ACM on So...· 0 citations
Fuzzing finds bugs by testing software behavior with high volumes of input. To create semantically valid inputs for different targets, traditional fuzzers require significant engineering effort. LLM-based fuzzing approaches can be adapted to create inputs for a wide range of software but introduce new issues: every tes...
Lu Maltsis· Companion Proceedings of the...· 0 citations
A seed optimization method called IRIS-Seed (Intelligent Reasoning and Integrated Scheduling for Path-Sensitive Seed Optimization) is presented, which consists of a chain-of-thought guided (CoT-guided) large language model (LLM) seed generation module, an execution-path collection module, and a path-sensitive seed sele...
Meng-Qi Kang, Chang-You Xing, Guo-Min Zhang et al.· Computers, Materials & C...· 0 citations
Compiler fuzzing is critical for ensuring the reliability of modern optimizing compilers. However, traditional generators and raw Large Language Model (LLM) outputs often yield syntactically invalid or low-value programs, incurring significant computational overhead. In this paper, we present BanditFuzz, an end-to-end...
Dong-Hui Li, Ying-Ying Li, Jin-Long Xu et al.· Proceedings of the 41st IEEE...· 0 citations
Automated unit test generation promises to reduce the cost of software quality assurance, and hence, is attracting attention from both academia and industry. Yet, generating assertions that are executable, meaningful to developers, and able to catch faults remains an unsolved challenge. Existing approaches either rando...
Jia-Lun Cao, Hao-Yu Wang, Hao-Ran Yan et al.· Proceedings of the ACM on So...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.