# Towards Understanding Deep Learning Model in Image Recognition via Coverage Test

arXiv: https://arxiv.org/abs/2505.08814 · HTML: https://mlsanity.com/paper/2505.08814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 71 references that are in the map.
- First posted on arXiv 12 May 2025.

## Builds on (most cited first, 29 of 29)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Securify: Practical Security Analysis of Smart Contracts](https://mlsanity.com/paper/1806.01143/) (2018)
- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [SourcererCC: Scaling Code Clone Detection to Big Code](https://mlsanity.com/paper/1512.06448/) (2015)
- [Testing Deep Neural Networks](https://mlsanity.com/paper/1803.04792/) (2018)
- [ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection](https://mlsanity.com/paper/2106.08890/) (2021)
- [Non-Fungible Token (NFT): Overview, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2105.07447/) (2021)
- [How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection](https://mlsanity.com/paper/2005.11613/) (2020)
- [SmartBugs: A Framework to Analyze Solidity Smart Contracts](https://mlsanity.com/paper/2007.04771/) (2020)
- [Black-Box Testing of Deep Neural Networks Through Test Case Diversity](https://mlsanity.com/paper/2112.12591/) (2021)
- [NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks](https://mlsanity.com/paper/2203.12915/) (2022)
- [ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts](https://mlsanity.com/paper/2403.06838/) (2024)
- [A Survey of Smart Contract Formal Specification and Verification](https://mlsanity.com/paper/2008.02712/) (2020)
- [Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion](https://mlsanity.com/paper/2112.01955/) (2021)
- [Neural network models and deep learning - a primer for biologists](https://mlsanity.com/paper/1902.04704/) (2019)
- [Checking Smart Contracts with Structural Code Embedding](https://mlsanity.com/paper/2001.07125/) (2020)
- [Smart Contract Vulnerability Detection Technique: A Survey](https://mlsanity.com/paper/2209.05872/) (2022)
- [StateGuard: Detecting State Derailment Defects in Decentralized Exchange Smart Contract](https://mlsanity.com/paper/2405.09181/) (2024)
- [Characterizing Code Clones in the Ethereum Smart Contract Ecosystem](https://mlsanity.com/paper/1905.00272/) (2019)
- [Malicious Code Detection in Smart Contracts via Opcode Vectorization](https://mlsanity.com/paper/2504.12720/) (2025)
- [CLUE: Towards Discovering Locked Cryptocurrencies in Ethereum](https://mlsanity.com/paper/2012.01370/) (2020)
- [Smart Contracts in the Real World: A Statistical Exploration of External Data Dependencies](https://mlsanity.com/paper/2406.13253/) (2024)
- [Detecting Malicious Accounts in Web3 through Transaction Graph](https://mlsanity.com/paper/2410.20713/) (2024)
- [Combining GPT and Code-Based Similarity Checking for Effective Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2412.18225/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) play a crucial role in the field of artificial intelligence, and their security-related testing has been a prominent research focus. By inputting test cases, the behavior of models is examined for anomalies, and coverage metrics are utilized to determine the extent of neurons covered by these test cases. With the widespread application and advancement of DNNs, different types of neural behaviors have garnered attention, leading to the emergence of various coverage metrics for neural networks. However, there is currently a lack of empirical research on these coverage metrics, specifically in analyzing the relationships and patterns between model depth, configuration information, and neural network coverage. This paper aims to investigate the relationships and patterns of four coverage metrics: primary functionality, boundary, hierarchy, and structural coverage. A series of empirical experiments were conducted, selecting LeNet, VGG, and ResNet as different DNN architectures, along with 10 models of varying depths ranging from 5 to 54 layers, to compare and study the relationships between different depths, configuration information, and various neural network coverage metrics. Additionally, an investigation was carried out on the relationships between modified decision/condition coverage and dataset size. Finally, three potential future directions are proposed to further contribute to the security testing of DNN Models.