CVE-2025-9906 HIGH

CVE-2025-9906: Arbitrary Code execution in Keras Safe Mode

Vendor Keras-Team
Product Keras
Weakness CWE-502 · Unsafe deserialization
Published September 19, 2025
Last update February 26, 2026

CVSS base score

8.6/10
Attack vector Local
Attack complexity Low
Privileges required Low
User interaction
Confidentiality
Integrity

CVSS vector

CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/AU:Y/R:A

What the vulnerability does

01Description

The Keras Model.load_model method can be exploited to achieve arbitrary code execution, even with safe_mode=True. One can create a specially crafted .keras model archive that, when loaded via Model.load_model, will trigger arbitrary code to be executed. This is achieved by crafting a special config.json (a file within the .keras archive) that will invoke keras.config.enable_unsafe_deserialization() to disable safe mode. Once safe mode is disable, one can use the Lambda layer feature of keras, which allows arbitrary Python code in the form of pickled code. Both can appear in the same archive. Simply the keras.config.enable_unsafe_deserialization() needs to appear first in the archive and the Lambda with arbitrary code needs to be second.

Key dates

02Disclosure timeline

September 19, 2025 CVE published
February 26, 2026 Record updated