Description
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.
References (6)
Core 6
Core References
Mailing List, Third Party Advisory mailing-list
http://seclists.org/fulldisclosure/2020/Nov/44
Third Party Advisory vendor-advisory
https://security.gentoo.org/glsa/202301-03
Exploit, Third Party Advisory, VDB Entry
http://packetstormsecurity.com/files/160281/SciKit-Learn-0.23.2-Denial-Of-Service.html
Exploit, Third Party Advisory
https://github.com/cjlin1/libsvm/blob/9a3a9708926dec87d382c43b203f2ca19c2d56a0/svm.cpp#L2501
Patch, Third Party Advisory
https://github.com/scikit-learn/scikit-learn/commit/1bf13d567d3cd74854aa8343fd25b61dd768bb85
Exploit, Issue Tracking, Third Party Advisory
https://github.com/scikit-learn/scikit-learn/issues/18891
Scores
CVSS v3
7.5
EPSS
0.0025
EPSS Percentile
48.3%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
partial
Details
Status
published
Products (2)
pypi/scikit-learn
0.23.2 - 1.0.1PyPI
scikit-learn/scikit-learn
0.23.2 - 1.0.1
Published
Nov 21, 2020
Tracked Since
Feb 18, 2026