Mend.io Vulnerability Database
The largest open source vulnerability database
What is a Vulnerability ID?
New vulnerability? Tell us about it!
WS-2024-0010
Published:May 15, 2026
Updated:May 15, 2026
In some settings, an adversary can perform a training data extraction attack to recover individual training examples by querying the language model. It finds that larger models are more vulnerable than smaller models.
Affected Packages
huggingface.co/d-matrix/gpt2 (ML_MODEL):
Affected version(s) =95db0b0bd2953a91ae670ec463e733544361e9c6 <caad9dc76345007099ab50f857ed66e828cf2d9c
Fix Suggestion:
Update to version caad9dc76345007099ab50f857ed66e828cf2d9c
huggingface.co/xared1001/gpt2-xl_pytorch (ML_MODEL):
Affected version(s) =667f89503deb47bc54e47aba3af6a0982e5e807c
Fix Suggestion:
Update to version no_fix
huggingface.co/openai-community/gpt2-xl (ML_MODEL):
Affected version(s) =96efdb14467c7d6bdbd49f6c6fbeeb273992cb4c <b81cf803a4e4e809062586ac620a06e65d9e20b6
Fix Suggestion:
Update to version b81cf803a4e4e809062586ac620a06e65d9e20b6
huggingface.co/migueldeguzmandev/gpt2xl-standard-test-purposes-only (ML_MODEL):
Affected version(s) =e746d59a065dcc60563c5c8cfce58dfadc3744f6 <0c1eece33d9d92045d7ccb6129a285b1a5e709e6
Fix Suggestion:
Update to version 0c1eece33d9d92045d7ccb6129a285b1a5e709e6
Do you need more information?
Contact Us
CVSS v4
Base Score:
6.9
Attack Vector
LOCAL
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
NONE
Vulnerable System Integrity
HIGH
Vulnerable System Availability
NONE
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
6.2
Attack Vector
LOCAL
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
HIGH
Availability
NONE