Detecting poisoning attacks on neural networks by activation clustering
US-11188789-B2 · Nov 30, 2021 · US
This page is not indexed by search engines while we improve data quality.
Carvalho Wilka patents
Carvalho Wilka is listed as an inventor on 4 patents in our database. Major assignees and classification codes are summarized below.
| Metric | Value |
|---|---|
| Inventor | Carvalho Wilka |
| Total patents | 4 |
| First publication | Oct 17, 2019 |
| Latest publication | Nov 30, 2021 |
Notable patents
Publications ranked by popularity score, then publication date.
Using gradients to detect backdoors in neural networks
US-11132444-B2 · Sep 28, 2021 · US
Detecting poisoning attacks on neural networks by activation clustering
US-2020050945-A1 · Feb 13, 2020 · US
Using Gradients to Detect Backdoors in Neural Networks
US-2019318099-A1 · Oct 17, 2019 · US
Recent patents
Latest publications not already listed above.
No data yet.
Major assignees
Companies most often associated with this inventor's publications.
| Assignee | Patents |
|---|---|
| IBM | 4 |
Top CPC classifications
Most common classification codes across this inventor's patents.
| CPC | Patents |
|---|---|
| G06N3/045 | 4 |
| G06N3/0464 | 4 |
| G06N3/09 | 4 |
| G06V30/10 | 2 |
| G06V30/19173 | 2 |