EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CrossProbe: LLM-Empowered Cross-Project Bug Detection for Deep Learning Frameworks

Hao Guan, Guangdong Bai, Yepang Liu

Proceedings of the ACM on Software Engineering · 22.06.2025 · 2 (ISSTA) · 2430-2452

DOI: 10.1145/3728984 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 22.06.2025. Verfasst von Hao Guan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep Learning (DL) models may introduce reliability challenges in the underlying DL frameworks. These frameworks may be prone to bugs that can lead to crash or wrong results, particularly when involving complex model architectures and substantial computational demands. Such framework bugs can disrupt DL applications, impacting customer experience and potentially causing financial losses. Traditional approaches to testing DL frameworks face limitations in adapting to the vast search space of model structures, diverse APIs, and the complexity of hybrid programming and hardware environments. Recent advancements using Large Language Models (LLMs) have improved DL framework fuzzing, but their efficacy depends heavily on the quality and diversity of input prompts, which are often constructed using single-framework data. In this paper, we propose an innovative approach for enhancing test generation for DL frameworks by leveraging “mirroring issues”—analogous bugs identified across different frameworks with common functionalities. Our approach is inspired by the fact that DL frameworks, such as PyTorch and TensorFlow, often share common bugs due to dependencies, developer errors, or edge-case inputs. We develop CrossProbe that utilizes LLMs to effectively learn from existing issues of one framework and transfer the acquired knowledge to generate test cases for finding mirroring issues in another framework, thus enabling crossframework bug detection. To overcome the challenges of test case generation arising from the incompatible functionalities and different implementations between frameworks, we introduce three processes: alignment, screening, and distinction . These processes help mitigate transfer errors by establishing API pair databases, filtering unsuitable cases, and highlighting cross-framework distinctions. Experiments demonstrate that CrossProbe is efficient by saving 36.3% iterations of generation, and achieves a 25.0% higher success rate in issue transferring compared to existing state-of-the-art LLM-based testing techniques. CrossProbe detects 24 unique bugs using its transferred knowledge. Out of them, 19 are previously unknown and each requires cross-framework knowledge in deep learning for identification.

Zitieren

APA

Guan, H., Bai, G., & Liu, Y. (2025). CrossProbe: LLM-Empowered Cross-Project Bug Detection for Deep Learning Frameworks. Proceedings of the ACM on Software Engineering, 2(ISSTA), 2430-2452. https://doi.org/10.1145/3728984

Vancouver

Guan H, Bai G, Liu Y. CrossProbe: LLM-Empowered Cross-Project Bug Detection for Deep Learning Frameworks. Proceedings of the ACM on Software Engineering. 2025;2(ISSTA):2430-2452. doi:10.1145/3728984

BibTeX
@article{Guan2025,
  author = {Guan, Hao and Bai, Guangdong and Liu, Yepang},
  title = {CrossProbe: LLM-Empowered Cross-Project Bug Detection for Deep Learning Frameworks},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2025},
  volume = {2},
  number = {ISSTA},
  pages = {2430--2452},
  doi = {10.1145/3728984}
}
Kostenlos starten →