Proj CDeepFuzz Paper Reading: Large Language Models are Zero-Shot Fuzzers:Fuzzing Deep-Learning Libraries via Large Language Models

Abstract

本文：TitanFuzz
Task: use LLM to fuzz DL librarires
Method: use both generative and infilling LLMs(e.g., Codex, InCoder)

实验：
对象：Tensorflow, PyTorch
Competitors: LEMON, Muffin, DeepREL, FreeFuzz
效果：

1. +30.38%/50.84% code coverage
2. detected 65 bugs, 41 confirmed