How do I poison an SVM with manifold regularization?

Question

I'm working on Adversarial Machine Learning, and have read multiple papers on this topic, some of them are mentioned as follows:

Poisoning Attacks on SVMs: https://arxiv.org/pdf/1206.6389.pdf
Adversarial Label Flips on Support Vector Machines

However, I am not able to find any literature on data poisoning for SVMs using Manifold regularization. Is there anyone who has knowledge about that?

I found the following Youtube video: [Poisoning Attacks against Support Vector Machines](https://www.youtube.com/watch?v=8dBasP-rhlY). Is it close to what you are looking for? — CoffeeBaconAddict, Mar 08 '20 at 06:46

score 0 · Answer 1 · answered Mar 09 '20 at 16:01

0

I think, one could generate a data set, with a random variable in each component of the data vector, add this data to the training data set, and then shuffle the combined data set.

answered Mar 09 '20 at 16:01

Jerry B

9
1

2

Can you please clarify how this answers the question? – nbro Mar 10 '20 at 01:00

How do I poison an SVM with manifold regularization?

1 Answers1