Security Resilience

CVE-2023-33976

Memory Safety in Google Tensorflow ≤ 2.13.0

Memory Safety
Published
30 July 2024
Modified
21 November 2024
Patch / advisory
View advisory
CVSS Score v3.1 7.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0043 36th percentile
Risk Priority 57 floored blend · peak EPSS

CVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.

Summary

CVE-2023-33976 is a high-severity Integer Overflow or Wraparound (CWE-190) vulnerability in Google Tensorflow. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique LSA Secrets (T1003.004); ranked at the 36th 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.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-8 (Security and Privacy Engineering Principles) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

TensorFlow is an end-to-end open source platform for machine learning. `array_ops.upper_bound` causes a segfault when not given a rank 2 tensor. The fix will be included in TensorFlow 2.13 and will also cherrypick this commit on TensorFlow 2.12.

CWE(s)
CWE-190

AI Security AnalysisAI

AI Category
Deep Learning Frameworks
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: tensorflow, machine learning, tensorflow, tensorflow

Related Threats

MITRE ATT&CK Enterprise Techniques

T1003.004 LSA Secrets Credential Access
Adversaries with SYSTEM access to a host may attempt to access Local Security Authority (LSA) secrets, which can contain a variety of different credential materials, such as credentials for service accounts.
attack.mitre.org →
T1003.005 Cached Domain Credentials Credential Access
Adversaries may attempt to access cached domain credentials used to allow authentication to occur in the event a domain controller is unavailable.
attack.mitre.org →
T1003.006 DCSync Credential Access
Adversaries may attempt to access credentials and other sensitive information by abusing a Windows Domain Controller's application programming interface (API)(Citation: Microsoft DRSR Dec 2017) (Citation: Microsoft GetNCCChanges) (Citati…
attack.mitre.org →
T1003.008 /etc/passwd and /etc/shadow Credential Access
Adversaries may attempt to dump the contents of <code>/etc/passwd</code> and <code>/etc/shadow</code> to enable offline password cracking.
attack.mitre.org →
T1006 Direct Volume Access Stealth
Adversaries may directly access a volume to bypass file access controls and file system monitoring.
attack.mitre.org →
T1008 Fallback Channels Command And Control
Adversaries may use fallback or alternate communication channels if the primary channel is compromised or inaccessible in order to maintain reliable command and control and to avoid data transfer thresholds.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-25662Same product: Google Tensorflow
CVE-2023-25667Same product: Google Tensorflow
CVE-2023-25664Same product: Google Tensorflow
CVE-2023-25668Same product: Google Tensorflow
CVE-2023-25659Same product: Google Tensorflow
CVE-2023-25658Same product: Google Tensorflow
CVE-2023-25671Same product: Google Tensorflow
CVE-2023-25801Same product: Google Tensorflow
CVE-2023-25670Same product: Google Tensorflow
CVE-2023-25669Same product: Google Tensorflow

Affected Assets

google
tensorflow
≤ 2.13.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)

—

Validate
Prove the fix (OWASP ASVS)
  • V5.2.6

Mitigating Controls (NIST 800-53 r5) AI

SA-11 Developer Testing and Evaluation good match

Developer testing and evaluation (static analysis, fuzzing, unit tests) directly finds integer overflow defects before deployment.

SA-8 Security and Privacy Engineering Principles partial match

Secure engineering principles require use of safe arithmetic constructs or language features that structurally eliminate integer overflow during calculation.

SI-10 Information Input Validation partial match

Input validation enforces bounds on values before arithmetic, stopping the conditions that trigger overflow or wraparound.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 partial match
blocks

Secure SDLC practices directly require use of safe arithmetic, bounds checks, and testing that prevent integer overflows.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.5.14 Information transfer partial match
removes
A.5.15 Access control partial match
removes
A.5.16 Identity management partial match
removes
A.5.17 Authentication information partial match
removes
A.5.18 Access rights partial match
removes
A.8.10 Information deletion partial match
removes

References