Anomaly Detection Based on Critical Paths for Deep Neural Networks

2025/05/20 by Fangzhen Zhao, Chenyi Zhang, Zhao, Fangzhen +7
Computer Science · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection

paper · pdf · doi:10.48550/arxiv.2505.14967

openalex publication_date 2025/05/20 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

Deep neural networks (DNNs) are notoriously hard to understand and difficult to defend. Extracting representative paths (including the neuron activation values and the connections between neurons) from DNNs using software engineering approaches has recently shown to be a promising approach in interpreting the decision making process of blackbox DNNs, as the extracted paths are often effective in capturing essential features. With this in mind, this work investigates a novel approach that extracts critical paths from DNNs and subsequently applies the extracted paths for the anomaly detection task, based on the observation that outliers and adversarial inputs do not usually induce the same activation pattern on those paths as normal (in-distribution) inputs. In our approach, we first identify critical detection paths via genetic evolution and mutation. Since different paths in a DNN often capture different features for the same target class, we ensemble detection results from multiple paths by integrating random subspace sampling and a voting mechanism. Compared with state-of-the-art methods, our experimental results suggest that our method not only outperforms them, but it is also suitable for the detection of a broad range of anomaly types with high accuracy.

Citations

• A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples
• A General Framework For Detecting Anomalous Inputs to DNN Classifiers
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data
• Adversarial Detection and Correction by Matching Prediction Distributions
• Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
• Detecting Adversarial Samples Using Influence Functions and Nearest Neighbors
• Likelihood Ratios for Out-of-Distribution Detection
• Deep Semi-Supervised Anomaly Detection
• Adversarial Defense Through Network Profiling Based Path Extraction
• Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
• Distilling Critical Paths in Convolutional Neural Networks
• Deep Anomaly Detection with Outlier Exposure
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Concolic Testing for Deep Neural Networks
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
• MagNet: a Two-Pronged Defense against Adversarial Examples
• Detecting Adversarial Samples from Artifacts
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Towards Evaluating the Robustness of Neural Networks
• Human-level concept learning through probabilistic program induction
• Deep Residual Learning for Image Recognition
• The Limitations of Deep Learning in Adversarial Settings
• DeepFool: a simple and accurate method to fool deep neural networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Inverting Visual Representations with Convolutional Networks
• TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking
• Explaining and Harnessing Adversarial Examples
• Deep Neural Networks are Easily Fooled: High Confidence Predictions for\n Unrecognizable Images
• ImageNet classification with deep convolutional neural networks
• A Fast Learning Algorithm for Deep Belief Nets
• Estimating the Support of a High-Dimensional Distribution

Related

• A Uniform Framework for Anomaly Detection in Deep Neural Networks
• A General Framework For Detecting Anomalous Inputs to DNN Classifiers
• AD-NEv++ : The multi-architecture neuroevolution-based multivariate anomaly detection framework
• Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection
• Subset Scanning Over Neural Network Activations