All the vulnerabilites related to scikit-learn - scikit-learn/scikit-learn
cve-2024-5206
Vulnerability from cvelistv5
Published
2024-06-06 18:28
Modified
2024-08-01 21:03
Severity ?
EPSS score ?
Summary
A sensitive data leakage vulnerability was identified in scikit-learn's TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the `stop_words_` attribute, rather than only storing the subset of tokens required for the TF-IDF technique to function. This behavior leads to the potential leakage of sensitive information, as the `stop_words_` attribute could contain tokens that were meant to be discarded and not stored, such as passwords or keys. The impact of this vulnerability varies based on the nature of the data being processed by the vectorizer.
References
Impacted products
Vendor | Product | Version | |
---|---|---|---|
▼ | scikit-learn | scikit-learn/scikit-learn |
Version: unspecified < 1.5.0 |
|
{ "containers": { "adp": [ { "affected": [ { "cpes": [ "cpe:2.3:a:scikit-learn:scikit-learn:*:*:*:*:*:*:*:*" ], "defaultStatus": "unknown", "product": "scikit-learn", "vendor": "scikit-learn", "versions": [ { "lessThan": "1.5.0", "status": "affected", "version": "0", "versionType": "custom" } ] } ], "metrics": [ { "other": { "content": { "id": "CVE-2024-5206", "options": [ { "Exploitation": "poc" }, { "Automatable": "no" }, { "Technical Impact": "partial" } ], "role": "CISA Coordinator", "timestamp": "2024-06-07T15:11:02.549686Z", "version": "2.0.3" }, "type": "ssvc" } } ], "providerMetadata": { "dateUpdated": "2024-06-07T15:12:13.507Z", "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP" }, "title": "CISA ADP Vulnrichment" }, { "providerMetadata": { "dateUpdated": "2024-08-01T21:03:11.034Z", "orgId": "af854a3a-2127-422b-91ae-364da2661108", "shortName": "CVE" }, "references": [ { "tags": [ "x_transferred" ], "url": "https://huntr.com/bounties/14bc0917-a85b-4106-a170-d09d5191517c" }, { "tags": [ "x_transferred" ], "url": "https://github.com/scikit-learn/scikit-learn/commit/70ca21f106b603b611da73012c9ade7cd8e438b8" } ], "title": "CVE Program Container" } ], "cna": { "affected": [ { "product": "scikit-learn/scikit-learn", "vendor": "scikit-learn", "versions": [ { "lessThan": "1.5.0", "status": "affected", "version": "unspecified", "versionType": "custom" } ] } ], "descriptions": [ { "lang": "en", "value": "A sensitive data leakage vulnerability was identified in scikit-learn\u0027s TfidfVectorizer, specifically in versions up to and including 1.4.1.post1, which was fixed in version 1.5.0. The vulnerability arises from the unexpected storage of all tokens present in the training data within the `stop_words_` attribute, rather than only storing the subset of tokens required for the TF-IDF technique to function. This behavior leads to the potential leakage of sensitive information, as the `stop_words_` attribute could contain tokens that were meant to be discarded and not stored, such as passwords or keys. The impact of this vulnerability varies based on the nature of the data being processed by the vectorizer." } ], "metrics": [ { "cvssV3_0": { "attackComplexity": "HIGH", "attackVector": "LOCAL", "availabilityImpact": "NONE", "baseScore": 4.7, "baseSeverity": "MEDIUM", "confidentialityImpact": "HIGH", "integrityImpact": "NONE", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.0/AV:L/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N", "version": "3.0" } } ], "problemTypes": [ { "descriptions": [ { "cweId": "CWE-921", "description": "CWE-921 Storage of Sensitive Data in a Mechanism without Access Control", "lang": "en", "type": "CWE" } ] } ], "providerMetadata": { "dateUpdated": "2024-06-17T18:56:36.616Z", "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "shortName": "@huntr_ai" }, "references": [ { "url": "https://huntr.com/bounties/14bc0917-a85b-4106-a170-d09d5191517c" }, { "url": "https://github.com/scikit-learn/scikit-learn/commit/70ca21f106b603b611da73012c9ade7cd8e438b8" } ], "source": { "advisory": "14bc0917-a85b-4106-a170-d09d5191517c", "discovery": "EXTERNAL" }, "title": "Sensitive Data Leakage in sklearn.feature_extraction.text.TfidfVectorizer in scikit-learn/scikit-learn" } }, "cveMetadata": { "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "assignerShortName": "@huntr_ai", "cveId": "CVE-2024-5206", "datePublished": "2024-06-06T18:28:14.267Z", "dateReserved": "2024-05-22T15:52:49.284Z", "dateUpdated": "2024-08-01T21:03:11.034Z", "state": "PUBLISHED" }, "dataType": "CVE_RECORD", "dataVersion": "5.1" }