How do I poison an SVM with manifold regularization?


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

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?


Posted 2020-02-18T00:50:39.247

Reputation: 105


I found the following Youtube video: Poisoning Attacks against Support Vector Machines. Is it close to what you are looking for?

– CoffeeBaconAddict – 2020-03-08T06:46:24.103



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.

Jerry B

Posted 2020-02-18T00:50:39.247

Reputation: 11

Can you please clarify how this answers the question? – nbro – 2020-03-10T01:00:10.883