Newest papers

Typed Template Fuzzing

Lu Maltsis · 2026 · ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH)

DOI: 10.1145/3837729.3839574 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

Fuzzing通过测试高输入量的软件行为来发现错误。为了为不同的目标创建语义有效的输入,传统的fuzzers需要大量的工程努力。基于LLM的fuzzing方法可以适应为广泛的软件创建输入,但引入新的问题:每个测试都需要一个LLM查询,牺牲传统的fuzzing的速度。我们引入Typed Template Fuzzing(TTF)。它使用LLM在预处理步骤中创建模板,以编码种子文件的语义信息。这些模板允许语义意识的突变,而无需分析器,类型检查器或进一步的LLM查询。我们在我们的工具Typos中实施了TTF。使用Typos我们运行了五个月的混淆活动,发现97个以前未发现的错误。Typos

Machine translation (Meta M2M100); the English original follows.

Abstract

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 test needs an LLM query, sacrificing the speed of traditional fuzzing. We introduce Typed Template Fuzzing (TTF). It uses LLMs in a preprocessing step to create templates which encode semantic information of seed files. These templates enable semantically-aware mutations without the need for a parser, type-checker, or further LLM queries. We have implemented TTF in our tool Typos. Using Typos we have run a five-month fuzzing campaign, finding 97 previously undiscovered bugs. Typos achieves a 94.7% rate of valid inputs across a wide range of formats including SMT-LIB2, C, C++, Go, Rust, SystemVerilog, Scala, Java, and domain-specific libraries such as PyTorch and Qiskit.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Fuzz testing, Computer science, Preprocessor, Template, Software, Programming language

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange