Towards Understanding Deep Learning Model in Image Recognition via Coverage Test

• URL: http://arxiv.org/abs/2505.08814v1
• Date: Mon, 12 May 2025 08:25:55 GMT
• Title: Towards Understanding Deep Learning Model in Image Recognition via Coverage Test
• Authors: Wenkai Li, Xiaoqi Li, Yingjie Mao, Yishun Wang,
• Abstract summary: 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.<n>This paper aims to investigate the relationships and patterns of four coverage metrics: primary functionality, boundary, hierarchy, and structural coverage.
• Score: 0.7529855084362796
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning [1.03590082373586]
  We develop a deep neural model that integrates multi-modal learning with domain adaptation techniques for classification.<n>Our model processes data from diverse sources in a sequential cyclic manner, allowing it to learn from multiple datasets and adapt to varying feature spaces.<n> Experimental results demonstrate that our proposed model significantly outperforms baseline neural models in classifying network intrusions.
  arXiv  Detail & Related papers  (2025-08-05T14:46:03Z)
• Cognitive Networks and Performance Drive fMRI-Based State Classification Using DNN Models [0.0]
  We employ two structurally different and complementary DNN-based models to classify individual cognitive states. We show that despite the architectural differences, both models consistently produce a robust relationship between prediction accuracy and individual cognitive performance.
  arXiv  Detail & Related papers  (2024-08-14T15:25:51Z)
• Designing deep neural networks for driver intention recognition [40.87622566719826]
  This paper applies neural architecture search to investigate the effects of the deep neural network architecture on a real-world safety critical application. A set of eight search strategies are evaluated for two driver intention recognition datasets.
  arXiv  Detail & Related papers  (2024-02-07T12:54:15Z)
• Structured Neural Networks for Density Estimation and Causal Inference [15.63518195860946]
  Injecting structure into neural networks enables learning functions that satisfy invariances with respect to subsets of inputs. We propose the Structured Neural Network (StrNN), which injects structure through masking pathways in a neural network.
  arXiv  Detail & Related papers  (2023-11-03T20:15:05Z)
• Automated Natural Language Explanation of Deep Visual Neurons with Large Models [43.178568768100305]
  This paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models. Our framework is designed to be compatible with various model architectures and datasets, automated and scalable neuron interpretation.
  arXiv  Detail & Related papers  (2023-10-16T17:04:51Z)
• Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation [55.80128181112308]
  We show that dimensionality and quasi-orthogonality of neural networks' feature space may jointly serve as network's performance discriminants. Our findings suggest important relationships between the networks' final performance and properties of their randomly initialised feature spaces.
  arXiv  Detail & Related papers  (2022-03-30T21:47:32Z)
• Epistemic Neural Networks [25.762699400341972]
  In principle, ensemble-based approaches produce effective joint predictions. But the computational costs of training large ensembles can become prohibitive. We introduce the epinet: an architecture that can supplement any conventional neural network.
  arXiv  Detail & Related papers  (2021-07-19T14:37:57Z)
• Learning Interpretable Models for Coupled Networks Under Domain Constraints [8.308385006727702]
  We investigate the idea of coupled networks by focusing on interactions between structural edges and functional edges of brain networks. We propose a novel formulation to place hard network constraints on the noise term while estimating interactions. We validate our method on multishell diffusion and task-evoked fMRI datasets from the Human Connectome Project.
  arXiv  Detail & Related papers  (2021-04-19T06:23:31Z)
• Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs [11.211251493663267]
  This paper presents a taxonomy of OOD outlier inputs based on their source and nature of uncertainty. We develop a novel integrated detection approach that uses multiple attributes corresponding to different types of outliers.
  arXiv  Detail & Related papers  (2021-03-23T15:33:58Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• Inter-layer Information Similarity Assessment of Deep Neural Networks Via Topological Similarity and Persistence Analysis of Data Neighbour Dynamics [93.4221402881609]
  The quantitative analysis of information structure through a deep neural network (DNN) can unveil new insights into the theoretical performance of DNN architectures. Inspired by both LS and ID strategies for quantitative information structure analysis, we introduce two novel complimentary methods for inter-layer information similarity assessment. We demonstrate their efficacy in this study by performing analysis on a deep convolutional neural network architecture on image data.
  arXiv  Detail & Related papers  (2020-12-07T15:34:58Z)
• Spiking Neural Networks -- Part II: Detecting Spatio-Temporal Patterns [38.518936229794214]
  Spiking Neural Networks (SNNs) have the unique ability to detect information in encoded-temporal signals. We review models and training algorithms for the dominant approach that considers SNNs as a Recurrent Neural Network (RNN) We describe an alternative approach that relies on probabilistic models for spiking neurons, allowing the derivation of local learning rules via gradient estimates.
  arXiv  Detail & Related papers  (2020-10-27T11:47:42Z)
• Towards Interaction Detection Using Topological Analysis on Neural Networks [55.74562391439507]
  In neural networks, any interacting features must follow a strongly weighted connection to common hidden units. We propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. A Persistence Interaction detection(PID) algorithm is developed to efficiently detect interactions.
  arXiv  Detail & Related papers  (2020-10-25T02:15:24Z)
• Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey [77.99182201815763]
  Deep Neural Networks (DNNs) achieve state-of-the-art results in many different problem settings. DNNs are often treated as black box systems, which complicates their evaluation and validation. One promising field, inspired by the success of convolutional neural networks (CNNs) in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations.
  arXiv  Detail & Related papers  (2020-06-30T14:56:05Z)
• The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures [179.66117325866585]
  We investigate a design space that is usually overlooked, i.e. adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by shrinking widened baseline networks and leads to superior performance. Experiments are conducted on various networks and datasets for image classification, visual tracking and image restoration.
  arXiv  Detail & Related papers  (2020-06-29T17:59:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.