Proj CDeepFuzz Paper Reading: NeuRI: Diversifying DNN Generation via Inductive Rule Inference

Abstract

背景：The correctness of DL systems is crucial for trust in DL applications
本文: NeuRI
BaseTool: FreeFuzz
Github: https://github.com/ise-uiuc/neuri-artifact
Task: Fuzzing DL Libraris and explore more types of operators
Step:

1. collecting valid and invalid API traces from various sources, 就是freefuzz
2. apply inductive program synthesis over traces to infer the constraints
3. hybrid fuzzing

实验：
对象：PyTorch, TensorFlow
Competitor: NNSmith
效果：

1. +51%, 15% branch coverage
2. detected 87 bugs, 64 confirmed, 8 high-priority bugs

本栏目推荐文章
• MLPerf™ 推理基准套件- mlcommons-inference
• [论文阅读] Self-conditioned Image Generation via Generating Representations
• 《A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction》阅读笔记
• [论文阅读] Learning Component-Level and Inter-Class Glyph Representation for few-shot Font Generation
• 【论文阅读笔记】【多模态-Vision-Language Pretraining】 BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
• 《REBEL Relation Extraction By End-to-end Language generation》阅读笔记
• Computer vision: models, learning and inference
• OpenSSL - Certificate Generation
• [论文阅读] Latent Consistency Models@ Synthesizing High-Resolution Images with Few-Step Inference
• 模型推理batch inference速度无明显提升、耗时线性增长问题排查

Diversifying Generation CDeepFuzz Inductive Inferencediversifying generation cdeepfuzz inductive understanding pre-trained generation cdeepfuzz coverage-guided generation cdeepfuzz coverage inductive diversifying inference mlcommons-inference inference computer learning vision inference paddle classification exploiting questions inference