cve/2020/CVE-2020-28975.md

### [CVE-2020-28975](https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2020-28975)
![](https://img.shields.io/static/v1?label=Product&message=n%2Fa&color=blue)
![](https://img.shields.io/static/v1?label=Version&message=n%2Fa&color=blue)
![](https://img.shields.io/static/v1?label=Vulnerability&message=n%2Fa&color=brighgreen)

### Description

** DISPUTED ** svm_predict_values in svm.cpp in Libsvm v324, as used in scikit-learn 0.23.2 and other products, allows attackers to cause a denial of service (segmentation fault) via a crafted model SVM (introduced via pickle, json, or any other model permanence standard) with a large value in the _n_support array. NOTE: the scikit-learn vendor's position is that the behavior can only occur if the library's API is violated by an application that changes a private attribute.

### POC

#### Reference
- http://packetstormsecurity.com/files/160281/SciKit-Learn-0.23.2-Denial-Of-Service.html
- https://github.com/scikit-learn/scikit-learn/issues/18891

#### Github
- https://github.com/Live-Hack-CVE/CVE-2020-28975