Timeline for Can I reverse engineer (parts of) the training data from a machine learning model?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 10, 2021 at 9:07 | vote | accept | 7824238 | ||
| Jul 5, 2021 at 15:12 | answer | added | Ben Reiniger♦ | timeline score: 3 | |
| Jul 3, 2021 at 21:37 | comment | added | Ubikuity | Welcome to SE datascience. That is a very interesting question there. I think it is very complicated to reverse engineer a model once trained. One thing worth noting tho is the fact that 0s in training datas are often considered as missing data. So maybe if you send vectors with 0s and few ones and observe the output, you can deduce some information about how the model works and what is the shape of the input data. | |
| Jul 3, 2021 at 20:34 | review | First posts | |||
| Jul 4, 2021 at 4:20 | |||||
| Jul 3, 2021 at 20:33 | history | asked | 7824238 | CC BY-SA 4.0 |