{"id":"PYSEC-2020-108","details":"** 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.","aliases":["CVE-2020-28975","GHSA-jxfp-4rvq-9h9m"],"modified":"2026-06-10T17:02:41.379397513Z","published":"2020-11-21T21:15:00Z","references":[{"type":"REPORT","url":"https://github.com/scikit-learn/scikit-learn/issues/18891"},{"type":"WEB","url":"https://github.com/cjlin1/libsvm/blob/9a3a9708926dec87d382c43b203f2ca19c2d56a0/svm.cpp#L2501"},{"type":"WEB","url":"http://seclists.org/fulldisclosure/2020/Nov/44"},{"type":"WEB","url":"http://packetstormsecurity.com/files/160281/SciKit-Learn-0.23.2-Denial-Of-Service.html"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-jxfp-4rvq-9h9m"}],"affected":[{"package":{"name":"scikit-learn","ecosystem":"PyPI","purl":"pkg:pypi/scikit-learn"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.24.dev0"}]}],"versions":["0.10","0.11","0.12","0.12.1","0.13","0.13.1","0.14","0.14.1","0.14a1","0.15.0","0.15.0b1","0.15.0b2","0.15.1","0.15.2","0.16.0","0.16.1","0.16b1","0.17","0.17.1","0.17b1","0.18","0.18.1","0.18.2","0.18rc2","0.19.0","0.19.1","0.19.2","0.19b2","0.20.0","0.20.1","0.20.2","0.20.3","0.20.4","0.20rc1","0.21.0","0.21.1","0.21.2","0.21.3","0.21rc2","0.22","0.22.1","0.22.2","0.22.2.post1","0.22rc2.post1","0.22rc3","0.23.0","0.23.0rc1","0.23.1","0.23.2","0.9"],"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/scikit-learn/PYSEC-2020-108.yaml"}}],"schema_version":"1.7.5"}