Adversarial Defense Through Network Profiling Based Path Extraction

2019/04/17 by Yuxian Qiu, Qiu, Yuxian, Jingwen Leng +11 · 1 citation
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Integrated Circuits and Semiconductor Failure Analysis #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1904.08089

openalex publication_date 2019/04/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/02

Abstract

Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input perturbation to the input image to fool the DNN models. This work proposes a profiling-based method to decompose the DNN models to different functional blocks, which lead to the effective path as a new approach to exploring DNNs' internal organization. Specifically, the per-image effective path can be aggregated to the class-level effective path, through which we observe that adversarial images activate effective path different from normal images. We propose an effective path similarity-based method to detect adversarial images with an interpretable model, which achieve better accuracy and broader applicability than the state-of-the-art technique.

Citations

• Backpropagation Applied to Handwritten Zip Code Recognition
• ImageNet classification with deep convolutional neural networks
• Adversarial Machine Learning at Scale
• Towards Deep Learning Models Resistant to Adversarial Attacks
• DeepFool: a simple and accurate method to fool deep neural networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models

Cited by

• Anomaly Detection Based on Critical Paths for Deep Neural Networks

Related

• Are classical deep neural networks weakly adversarially robust?
• Analyzing the Noise Robustness of Deep Neural Networks
• AdvDrop: Adversarial Attack to DNNs by Dropping Information
• Detecting Adversarial Examples
• AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings