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

Arabic

وتتطلب Fuzzers التقليدية جهودًا إبداعية كبيرة من أجل إنشاء الملفات من خلال اختبار سلوك البرمجيات مع كميات كبيرة من الملفات. من أجل إنشاء الملفات القائمة على الأهداف المختلفة، فإن Fuzzers التقليدية تتطلب جهودًا إبداعية كبيرة. ويمكن تطبيق نهج Fuzzing LLM لإنشاء الملفات القائمة على مجموعة واسعة من البرمجيات، ولكن يتم إدخال مشاكل جديدة: كل اختبار يحتاج إلى سؤال LLM، ويحتاج إلى زيادة سرعة Fuzzing التقليدية. ونحن نقدم TTF في أداة Typed Template Fuzzing (TTF). باستخدام Typos، نحن نستخدم LLM في خطة إبداعية لمدة خمس أشهر لإنشاء الملفات التي تحكم معلومات

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31342, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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