Adversarial Defense Through Network Profiling Based Path Extraction
| Autor: | Chao Li, Yuhao Zhu, Cong Guo, Jingwen Leng, Yuxian Qiu, Minyi Guo, Quan Chen |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer Science - Cryptography and Security Artificial neural network business.industry Computer science Deep learning Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Machine Learning (stat.ML) computer.software_genre Machine Learning (cs.LG) Adversarial system Statistics - Machine Learning Data mining Artificial intelligence business computer Feature learning Cryptography and Security (cs.CR) Internal organization |
| Zdroj: | CVPR |
| DOI: | 10.48550/arxiv.1904.08089 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|