EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models

Chenyuan Yang, Yinlin Deng, Runyu Lu, Jiayi Yao, Jiawei Liu, Reyhaneh Jabbarvand, Lingming Zhang

Proceedings of the ACM on Programming Languages · 08.10.2024 · 8 (OOPSLA2) · 709-735

DOI: 10.1145/3689736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 08.10.2024. Verfasst von Chenyuan Yang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 87-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Compiler correctness is crucial, as miscompilation can falsify program behaviors, leading to serious consequences over the software supply chain. In the literature, fuzzing has been extensively studied to uncover compiler defects. However, compiler fuzzing remains challenging: Existing arts focus on black- and grey-box fuzzing, which generates test programs without sufficient understanding of internal compiler behaviors. As such, they often fail to construct test programs to exercise intricate optimizations. Meanwhile, traditional white-box techniques, such as symbolic execution, are computationally inapplicable to the giant codebase of compiler systems. Recent advances demonstrate that Large Language Models (LLMs) excel in code generation/understanding tasks and even have achieved state-of-the-art performance in black-box fuzzing. Nonetheless, guiding LLMs with compiler source-code information remains a missing piece of research in compiler testing. To this end, we propose W hite F ox , the first white-box compiler fuzzer using LLMs with source-code information to test compiler optimization, with a spotlight on detecting deep logic bugs in the emerging deep learning (DL) compilers. W hite F ox adopts a multi-agent framework: (i) an LLM-based analysis agent examines the low-level optimization source code and produces requirements on the high-level test programs that can trigger the optimization; (ii) an LLM-based generation agent produces test programs based on the summarized requirements. Additionally, optimization-triggering tests are also used as feedback to further enhance the test generation prompt on the fly. Our evaluation on the three most popular DL compilers ( i.e ., PyTorch Inductor, TensorFlow-XLA, and TensorFlow Lite) shows that W hite F ox can generate high-quality test programs to exercise deep optimizations requiring intricate conditions, practicing up to 8 times more optimizations than state-of-the-art fuzzers. To date, W hite F ox has found in total 101 bugs for the compilers under test, with 92 confirmed as previously unknown and 70 already fixed. Notably, W hite F ox has been recently acknowledged by the PyTorch team, and is in the process of being incorporated into its development workflow. Finally, beyond DL compilers, W hite F ox can also be adapted for compilers in different domains, such as LLVM, where WHiteFox has already found multiple bugs.

Zitieren

APA

Yang, C., Deng, Y., Lu, R., Yao, J., Liu, J., Jabbarvand, R., & Zhang, L. (2024). WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models. Proceedings of the ACM on Programming Languages, 8(OOPSLA2), 709-735. https://doi.org/10.1145/3689736

Vancouver

Yang C, Deng Y, Lu R, Yao J, Liu J, Jabbarvand R, et al. WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models. Proceedings of the ACM on Programming Languages. 2024;8(OOPSLA2):709-735. doi:10.1145/3689736

BibTeX
@article{Yang2024,
  author = {Yang, Chenyuan and Deng, Yinlin and Lu, Runyu and Yao, Jiayi and Liu, Jiawei and Jabbarvand, Reyhaneh and Zhang, Lingming},
  title = {WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2024},
  volume = {8},
  number = {OOPSLA2},
  pages = {709--735},
  doi = {10.1145/3689736}
}
Kostenlos starten →