CVE-2020-28975

mediumpriority · track · 31EPSS 0.035 · 89 %ileEUNLRUUS

grimoire priorityP3 · Track

Exploitable?

—

no known exploitation

Likely / severe?

3.50% (89th) EPSS

CVSS 5 · medium

Is it mine?

7 products

Check your exposure

Who says so?

6 sources

cnnvd · enisa_euvd · fstec_bdu · osv

EPSS · scored 2026-10-27

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.

cvss

Technical severity, 0–10. One row per scoring source.

7.5

010

base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 5–7.5

v2.05mediumAV:N/AC:L/Au:N/C:N/I:N/A:Pprimary · NVD / NIST USexploitability 10 · impact 2.9

v3.17.5highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hprimary · NVD / NIST USexploitability 3.9 · impact 3.6

v3.17.5highAV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hsecondary · FSTEC (BDU) RU

v3.17.5highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hsecondary · OSV

v3.16.9mediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H/E:Usecondary · CVSS-BT (t0sche)

v3.17.5highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hsecondary · NCSC-NL NL

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: poc · Automatable: no · Technical Impact: partialcoordinatorcisa_ssvcUS

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-119USCWE-404US

affected products (7)

Products and version ranges known to be affected.

n/a n/a≤ n/aenisa_euvdEU
Scikit-Learn Scikit-Learn0.23.2 → 1.1.1fstec_bduRU
Сообщество свободного программного обеспечения Libsvm≤ 324fstec_bduRU
business_intelligenceall versionsncsc_nlNLcpe:2.3:a:oracle:business_intelligence:7.0.0.0.0:*:*:*:enterprise:*:*:*
scikit-learn scikit-learn0.23.2 → 1.0.1nvdUScpe:2.3:a:scikit-learn:scikit-learn:*:*:*:*:*:*:*:*
PyPI scikit-learn< 0.24.dev0osvUSpkg:pypi/scikit-learn
PyPI scikit-learn0.23.2 → 1.0.1osvUSpkg:pypi/scikit-learn

advisories (3)

Vendor and ecosystem advisories describing this.

NCSC-2025-0028Kwetsbaarheden verholpen in Oracle AnalyticsNL2025-01-22csaf · ncsc_nlNL
Oracle heeft kwetsbaarheden verholpen in Oracle Analytics producten, zoals Business Intelligence, Analytics Desktop en BI Publisher.
GHSA-jxfp-4rvq-9h9mscikit-learn Denial of Service2022-05-24ghsa · osvUS
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.
PYSEC-2020-1082020-11-21vendor · osvUS
** 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.

also known as (7)

Other names and identifiers for this entity.

sources

Which sources assert this record, and when.

cnnvd enisa_euvd fstec_bdu osv ncsc_nl nvd NVD CVE.org MITRE

published 2020-11-21modified 2026-06-17

references (21)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan