Abstract | ||
---|---|---|
Adversarial Robustness is a growing field that evidences the brittleness of neural networks. Although the literature on adversarial robustness is vast, a dimension is missing in these studies: assessing how severe the mistakes are. We call this notion "Adversarial Severity" since it quantifies the downstream impact of adversarial corruptions by computing the semantic error between the misclassific... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCVW54120.2021.00013 | 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) |
Keywords | DocType | ISSN |
Training,Computer vision,Conferences,Semantics,Neural networks,Benchmark testing,Extraterrestrial measurements | Conference | 2473-9936 |
ISBN | Citations | PageRank |
978-1-6654-0191-3 | 0 | 0.34 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guillaume Jeanneret | 1 | 0 | 1.35 |
Juan C Perez | 2 | 0 | 0.34 |
Pablo Arbelaez | 3 | 3626 | 173.00 |