CVE-2026-1669: Arbitrary file read in the model loading mechanism (HDF5 integration) in Keras versions 3.0.0 through 3.13.1 on all supp
highvulnerability
security
Summary
CVE-2026-1669 is a vulnerability in Keras (a machine learning library) versions 3.0.0 through 3.13.1 that allows attackers to read arbitrary files on a system by uploading a specially crafted model file that exploits HDF5 external dataset references (a feature of HDF5, a file format commonly used to store large amounts of numerical data). An attacker could use this to access sensitive information stored on the affected computer.
Vulnerability Details
EPSS (30-day exploit probability)
EPSS: 0.0%
Classification
Attack Type
Data Extraction
Attack SophisticationModerate
Impact (CIA+S)
confidentiality
AI Component TargetedModel
Affected Vendors
Google
Related Issues
Monthly digest — independent AI security research
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-1669
First tracked: February 12, 2026 at 03:04 PM
Classified by LLM (prompt v3) · confidence: 95%