CVE-2025-49655
Published: 17 October 2025
Summary
CVE-2025-49655 is a critical-severity Deserialization of Untrusted Data (CWE-502) vulnerability in Hiddenlayer (inferred from references). Its CVSS base score is 9.8 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Python (T1059.006); ranked at the 15.3th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Deep Learning Frameworks; in the Supply Chain and Deployment risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-34892
Vulnerability details
Deserialization of untrusted data can occur in versions of the Keras framework running versions 3.11.0 up to but not including 3.11.3, enabling a maliciously uploaded Keras file containing a TorchModuleWrapper class to run arbitrary code on an end user’s system…
more
when loaded despite safe mode being enabled. The vulnerability can be triggered through both local and remote files.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Deep Learning Frameworks
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: keras
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Deserialization of untrusted data in Keras enables arbitrary code execution via malicious files (local/remote) using Python interpreter despite safe mode, facilitating Python abuse, client execution exploitation, and defense evasion via exploitation.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Penetration testing supplies malicious serialized objects, detecting unsafe deserialization and supporting corrective actions.
Evaluation of untrusted data handling (deserialization testing) reveals unsafe processing, which the required remediation process addresses.
Untrusted serialized data can be deserialized and observed inside the chamber, blocking gadget-chain exploitation outside the sandbox.
Validates or rejects untrusted serialized data before deserialization occurs.
Identifies and blocks malicious code introduced through deserialization of untrusted data at system boundaries.
Integrity verification of serialized information can detect tampering before deserialization occurs.
Provenance of associated data allows detection of untrusted sources before deserialization or processing occurs.