Abstract | ||
---|---|---|
Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a targeted, incorrect classification on any input which contains the trigger. In this paper, we present the first ultra light-weight and highly effective trojan det... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCVW54120.2021.00008 | 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) |
Keywords | DocType | Volume |
Training,Deep learning,Computer vision,Conferences,Computational modeling,Computer architecture,Trojan horses | Conference | 2021 |
Issue | ISSN | ISBN |
1 | 2473-9936 | 978-1-6654-0191-3 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Greg Fields | 1 | 0 | 0.68 |
Mohammad Samragh | 2 | 38 | 7.01 |
Mojan Javaheripi | 3 | 18 | 5.83 |
Farinaz Koushanfar | 4 | 3055 | 268.84 |
Tara Javidi | 5 | 806 | 78.83 |