icon

We found results for “

WS-2024-0007

Date: April 11, 2024

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.

Language: ML

Severity Score

Severity Score

CVSS v3.1

Base Score:
Attack Vector (AV): LOCAL
Attack Complexity (AC): LOW
Privileges Required (PR): NONE
User Interaction (UI): NONE
Scope (S): UNCHANGED
Confidentiality (C): NONE
Integrity (I): LOW
Availability (A): NONE

Do you need more information?

Contact Us