Name
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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.00491 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Profiling (computer programming),Artificial intelligence,Artificial neural network,Machine learning,Semantics,Mathematics,Adversarial system | Journal | abs/1904.08089 |
ISSN | Citations | PageRank |
1063-6919 | 2 | 0.36 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuxian Qiu | 1 | 7 | 2.45 |
| Jingwen Leng | 2 | 49 | 12.97 |
| Cong Guo | 3 | 3 | 1.05 |
| Quan Chen | 4 | 175 | 21.86 |
| Chao Li | 5 | 344 | 37.85 |
| Minyi Guo | 6 | 3969 | 332.25 |
| Yuhao Zhu | 7 | 242 | 23.06 |