CVE-2022-29192: TensorFlow DoS — MEDIUM

CISO Take

A local attacker with low privileges can crash TensorFlow processes by passing malformed arguments to the QuantizeAndDequantizeV4Grad op, triggering a CHECK-failure assertion. Patch immediately to TF 2.6.4, 2.7.2, 2.8.1, or 2.9.0+ if your ML infrastructure runs on affected versions. Risk is limited to availability — no data exfiltration or code execution vector exists here.

What is the risk?

Medium severity with limited real-world blast radius. The local attack vector (AV:L) is the key constraint — an adversary needs an existing foothold on the machine running TensorFlow. In shared ML compute environments (JupyterHub clusters, multi-tenant GPU nodes, CI/CD runners), this becomes more concerning since a low-privileged user could disrupt training jobs or crash inference services. CVSS 5.5 is accurate; exploitability is straightforward once local access exists, but gaining that access is the hard part.

What systems are affected?

Package	Ecosystem	Vulnerable Range	Patched
TensorFlow	pip	—	No patch
195.8K OpenSSF 7.1 3.7K dependents Pushed 2d ago 4% patched ~1372d to patch Full package profile →

Do you use TensorFlow? You're affected.

How severe is it?

CVSS 3.1

5.5 / 10

EPSS

0.3%

chance of exploitation in 30 days

Higher than 26% of all CVEs

Source: EPSS v3 — FIRST.org

Exploitation Status

Exploit Available

Exploitation: MEDIUM

Sophistication

Moderate

Exploitation Confidence

medium

○ CISA SSVC: Public PoC

○ Public PoC indexed (trickest/cve)

Composite signal derived from CISA KEV, VulnCheck KEV, CISA SSVC, EPSS, Metasploit, Exploit-DB, trickest/cve, Nuclei templates, and inthewild.io exploitation reports.

What is the attack surface?

AV Local

AC Low

PR Low

UI None

S Unchanged

C None

I None

A High

What should I do?

5 steps

Patch: Upgrade TensorFlow to 2.6.4, 2.7.2, 2.8.1, or 2.9.0+. Verify via pip show tensorflow.
Isolation: Restrict local access to ML compute nodes — minimize shared JupyterHub instances and enforce per-user containerization.
Input validation: If accepting external model inference requests, validate and sanitize gradient operation inputs at the API boundary before passing to TF ops.
Detection: Monitor for abnormal TensorFlow process crashes (CHECK-failure logs contain 'Check failed:'); correlate with unexpected local logins or CI job failures.
Workaround: If patching is not immediately possible, disable or restrict access to raw TF op endpoints.

What does CISA's SSVC say?

Decision Track*

Exploitation poc

Automatable No

Technical Impact partial

Source: CISA Vulnrichment (SSVC v2.0). Decision based on the CISA Coordinator decision tree.

How is it classified?

DoS Framework AML.T0010.001 - AI Software AML.T0029 - Denial of AI Service AML.T0043.003 - Manual Modification

Which compliance frameworks are affected?

This CVE is relevant to:

EU AI Act

Article 15 - Accuracy, robustness and cybersecurity

ISO 42001

A.6.2 - AI system processes

NIST AI RMF

MANAGE 2.2 - Mechanisms are in place and applied to sustain the value of deployed AI systems

OWASP LLM Top 10

LLM09 - Overreliance

Frequently Asked Questions

What is CVE-2022-29192?

A local attacker with low privileges can crash TensorFlow processes by passing malformed arguments to the QuantizeAndDequantizeV4Grad op, triggering a CHECK-failure assertion. Patch immediately to TF 2.6.4, 2.7.2, 2.8.1, or 2.9.0+ if your ML infrastructure runs on affected versions. Risk is limited to availability — no data exfiltration or code execution vector exists here.

Is CVE-2022-29192 actively exploited?

Proof-of-concept exploit code is publicly available for CVE-2022-29192, increasing the risk of exploitation.

How to fix CVE-2022-29192?

1. Patch: Upgrade TensorFlow to 2.6.4, 2.7.2, 2.8.1, or 2.9.0+. Verify via `pip show tensorflow`. 2. Isolation: Restrict local access to ML compute nodes — minimize shared JupyterHub instances and enforce per-user containerization. 3. Input validation: If accepting external model inference requests, validate and sanitize gradient operation inputs at the API boundary before passing to TF ops. 4. Detection: Monitor for abnormal TensorFlow process crashes (CHECK-failure logs contain 'Check failed:'); correlate with unexpected local logins or CI job failures. 5. Workaround: If patching is not immediately possible, disable or restrict access to raw TF op endpoints.

What systems are affected by CVE-2022-29192?

This vulnerability affects the following AI/ML architecture patterns: training pipelines, model serving, model compression workflows, MLOps platforms.

What is the CVSS score for CVE-2022-29192?

CVE-2022-29192 has a CVSS v3.1 base score of 5.5 (MEDIUM). The EPSS exploitation probability is 0.34%.

What is the AI security impact?

Affected AI Architectures

training pipelinesmodel servingmodel compression workflowsMLOps platforms

MITRE ATLAS Techniques

AML.T0010.001 AI Software

AML.T0029 Denial of AI Service

AML.T0043.003 Manual Modification

Compliance Controls Affected

EU AI Act: Article 15

ISO 42001: A.6.2

NIST AI RMF: MANAGE 2.2

OWASP LLM Top 10: LLM09

What are the technical details?

Original Advisory

TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implementation of `tf.raw_ops.QuantizeAndDequantizeV4Grad` does not fully validate the input arguments. This results in a `CHECK`-failure which can be used to trigger a denial of service attack. Versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4 contain a patch for this issue.

Exploitation Scenario

An insider threat or attacker who has compromised a data scientist's account on a shared ML cluster deliberately calls `tf.raw_ops.QuantizeAndDequantizeV4Grad` with crafted tensor arguments that fail internal validation checks. The resulting CHECK-failure crashes the TensorFlow process, killing ongoing training jobs and potentially corrupting checkpoints. In a multi-tenant Kubernetes environment with a shared TF serving deployment, the same input sent to a quantized model's inference endpoint terminates the serving pod, causing a denial of service affecting all downstream applications consuming that model.

Weaknesses (CWE)

CWE-20 Improper Input Validation

CWE-20 — Improper Input Validation: The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

[Architecture and Design] Consider using language-theoretic security (LangSec) techniques that characterize inputs using a formal language and build "recognizers" for that language. This effectively requires parsing to be a distinct layer that effectively enforces a boundary between raw input and internal data representations, instead of allowing parser code to be scattered throughout the program, where it could be subject to errors or inconsistencies that create weaknesses. [REF-1109] [REF-1110] [REF-1111]
[Architecture and Design] Use an input validation framework such as Struts or the OWASP ESAPI Validation API. Note that using a framework does not automatically address all input validation problems; be mindful of weaknesses that could arise from misusing the framework itself (CWE-1173).

Source: MITRE CWE corpus.