PyTorch

'PyTorch' is a deep learning library that serves as a benchmark for evaluating the detection of silent bugs in deep learning applications through the use of historical bug reports and large language models.

Papers using PyTorch (11)

Your Fix Is My Exploit: Enabling Comprehensive DL Library API Fuzzing with Large Language Models2025 · 3 citesToward Compiler World Models: Learning Latent Dynamics for Efficient Tensor Program Search2026LLM-Powered Silent Bug Fuzzing in Deep Learning Libraries via Versatile and Controlled Bug Transfer2026MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing2025Evaluating the Effectiveness of Coverage-Guided Fuzzing for Testing Deep Learning Library APIs2025Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects2025Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models2022 · 13 citesToward Understanding Deep Learning Framework Bugs2022 · 10 citesAutomatic Unit Test Generation for Deep Learning Frameworks based on API Knowledge2023 · 1 citesEnhancing Differential Testing With LLMs For Testing Deep Learning Libraries2024 · 1 citesSecurity Knowledge-Guided Fuzzing of Deep Learning Libraries2023