# NeuRI: Diversifying DNN Generation via Inductive Rule Inference

arXiv: https://arxiv.org/abs/2302.02261 · HTML: https://mlsanity.com/paper/2302.02261/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 65 references that are in the map.
- First posted on arXiv 4 Feb 2023.

## Builds on (most cited first, 15 of 15)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models](https://mlsanity.com/paper/2212.14834/) (2022)
- [NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers](https://mlsanity.com/paper/2207.13066/) (2022)
- [Free Lunch for Testing: Fuzzing Deep-Learning Libraries from Open Source](https://mlsanity.com/paper/2201.06589/) (2022)
- [TF-Coder: Program Synthesis for Tensor Manipulations](https://mlsanity.com/paper/2003.09040/) (2020)
- [DocTer: Documentation Guided Fuzzing for Testing Deep Learning API Functions](https://mlsanity.com/paper/2109.01002/) (2021)
- [A Theory of Formal Synthesis via Inductive Learning](https://mlsanity.com/paper/1505.03953/) (2015)
- [Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing](https://mlsanity.com/paper/2204.08734/) (2022)
- [Fuzzing Deep-Learning Libraries via Automated Relational API Inference](https://mlsanity.com/paper/2207.05531/) (2022)
- [Rewrite Rule Inference Using Equality Saturation](https://mlsanity.com/paper/2108.10436/) (2021)
- [Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation](https://mlsanity.com/paper/2202.09947/) (2022)
- [SOAR: A Synthesis Approach for Data Science API Refactoring](https://mlsanity.com/paper/2102.06726/) (2021)
- [Graph-Based Fuzz Testing for Deep Learning Inference Engine](https://mlsanity.com/paper/2008.05933/) (2020)
- [A Static Analyzer for Detecting Tensor Shape Errors in Deep Neural Network Training Code](https://mlsanity.com/paper/2112.09037/) (2021)

## Built on by (most cited first, 7 of 7)

- [WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models](https://mlsanity.com/paper/2310.15991/) (2023)
- [Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks](https://mlsanity.com/paper/2506.14813/) (2025)
- [Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers](https://mlsanity.com/paper/2509.11173/) (2025)
- [Deep Learning Library Testing: Definition, Methods and Challenges](https://mlsanity.com/paper/2404.17871/) (2024)
- [Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging](https://mlsanity.com/paper/2404.09151/) (2024)
- [Demystifying the Silence of Correctness Bugs in PyTorch Compiler](https://mlsanity.com/paper/2604.08720/) (2026)
- [Grounding Deep Learning Framework Testing in Data Flow](https://mlsanity.com/paper/2610.15808/) (2026)

## Abstract (arXiv)

Deep Learning (DL) is prevalently used in various industries to improve decision-making and automate processes, driven by the ever-evolving DL libraries and compilers. The correctness of DL systems is crucial for trust in DL applications. As such, the recent wave of research has been studying the automated synthesis of test-cases (i.e., DNN models and their inputs) for fuzzing DL systems. However, existing model generators only subsume a limited number of operators, lacking the ability to pervasively model operator constraints. To address this challenge, we propose NeuRI, a fully automated approach for generating valid and diverse DL models composed of hundreds of types of operators. NeuRI adopts a three-step process: (i) collecting valid and invalid API traces from various sources; (ii) applying inductive program synthesis over the traces to infer the constraints for constructing valid models; and (iii) using hybrid model generation which incorporates both symbolic and concrete operators. Our evaluation shows that NeuRI improves branch coverage of TensorFlow and PyTorch by 24% and 15% over the state-of-the-art model-level fuzzers. NeuRI finds 100 new bugs for PyTorch and TensorFlow in four months, with 81 already fixed or confirmed. Of these, 9 bugs are labelled as high priority or security vulnerability, constituting 10% of all high-priority bugs of the period. Open-source developers regard error-inducing tests reported by us as "high-quality" and "common in practice".