CVE-2022-41888 — HIGH (CVSS 7.5) AI Security Vulnerability

CISO Take

A missing rank validation in TensorFlow's GPU-accelerated bounding box operation allows unauthenticated remote attackers to crash any inference service exposing this functionality. If your computer vision or object detection pipelines run on GPU-backed TensorFlow Serving endpoints, this is a live DoS vector. Patch immediately to TF 2.11, 2.10.1, 2.9.3, or 2.8.4.

Risk Assessment

CVSS 7.5 with network vector, low complexity, no authentication required makes this trivially exploitable against exposed endpoints. Impact is limited to availability — no data exfiltration or code execution path identified. Real-world risk is elevated for AI infrastructure teams running GPU-accelerated object detection or autonomous systems pipelines behind internal or external APIs. The lack of CISA KEV listing and no known active exploitation reduces urgency slightly, but the low barrier to exploit justifies prompt patching.

Affected Systems

Package	Ecosystem	Vulnerable Range	Patched
tensorflow	pip	—	No patch
195.0K OpenSSF 7.2 3.7K dependents Pushed today 4% patched ~1372d to patch Full package profile →

Do you use tensorflow? You're affected.

Severity & Risk

CVSS 3.1

7.5 / 10

EPSS

0.2%

chance of exploitation in 30 days

Higher than 45% of all CVEs

Source: EPSS v3 — FIRST.org

Exploitation Status

Exploit Available

Exploitation: MEDIUM

Sophistication

Trivial

Exploitation Confidence

medium

○ CISA SSVC: Public PoC

○ Public PoC indexed (trickest/cve)

Composite signal derived from CISA KEV, CISA SSVC, EPSS, trickest/cve, and Nuclei templates.

Attack Surface

AV Network

AC Low

PR None

UI None

S Unchanged

C None

I None

A High

Recommended Action

5 steps

PATCH

Upgrade to TensorFlow 2.11, 2.10.1, 2.9.3, or 2.8.4 — all contain commit cf35502.
WORKAROUND

Add explicit rank assertion before passing scores tensor to the op (e.g., tf.debugging.assert_rank(scores, 4)).
INPUT VALIDATION

Enforce tensor shape validation at API gateway or gRPC interceptor layer before requests reach the model server.
NETWORK HARDENING

Ensure TF Serving gRPC (port 8500) and REST (port 8501) endpoints are not internet-facing without authentication.
DETECTION

Monitor for repeated inference service crashes or GPU process restarts as a potential exploitation indicator.

CISA SSVC Assessment

Decision Track*

Exploitation poc

Automatable No

Technical Impact partial

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

Classification

DoS Framework Inference AML.T0029 - Denial of AI Service AML.T0046 - Spamming AI System with Chaff Data AML.T0049 - Exploit Public-Facing Application

Compliance Impact

This CVE is relevant to:

EU AI Act

Article 15 - Accuracy, robustness and cybersecurity for high-risk AI systems

ISO 42001

8.4 - AI System Operation

NIST AI RMF

GOVERN 6.2 - Policies and procedures are in place for AI risk management MANAGE 2.2 - Mechanisms to achieve AI risk management objectives are planned and in place

Frequently Asked Questions

What is CVE-2022-41888?

A missing rank validation in TensorFlow's GPU-accelerated bounding box operation allows unauthenticated remote attackers to crash any inference service exposing this functionality. If your computer vision or object detection pipelines run on GPU-backed TensorFlow Serving endpoints, this is a live DoS vector. Patch immediately to TF 2.11, 2.10.1, 2.9.3, or 2.8.4.

Is CVE-2022-41888 actively exploited?

Proof-of-concept exploit code is publicly available for CVE-2022-41888, increasing the risk of exploitation.

How to fix CVE-2022-41888?

1. PATCH: Upgrade to TensorFlow 2.11, 2.10.1, 2.9.3, or 2.8.4 — all contain commit cf35502. 2. WORKAROUND: Add explicit rank assertion before passing scores tensor to the op (e.g., tf.debugging.assert_rank(scores, 4)). 3. INPUT VALIDATION: Enforce tensor shape validation at API gateway or gRPC interceptor layer before requests reach the model server. 4. NETWORK HARDENING: Ensure TF Serving gRPC (port 8500) and REST (port 8501) endpoints are not internet-facing without authentication. 5. DETECTION: Monitor for repeated inference service crashes or GPU process restarts as a potential exploitation indicator.

What systems are affected by CVE-2022-41888?

This vulnerability affects the following AI/ML architecture patterns: model serving, training pipelines, inference.

What is the CVSS score for CVE-2022-41888?

CVE-2022-41888 has a CVSS v3.1 base score of 7.5 (HIGH). The EPSS exploitation probability is 0.23%.

Technical Details

NVD Description

TensorFlow is an open source platform for machine learning. When running on GPU, `tf.image.generate_bounding_box_proposals` receives a `scores` input that must be of rank 4 but is not checked. We have patched the issue in GitHub commit cf35502463a88ca7185a99daa7031df60b3c1c98. The fix will be included in TensorFlow 2.11. We will also cherrypick this commit on TensorFlow 2.10.1, 2.9.3, and TensorFlow 2.8.4, as these are also affected and still in supported range.

Exploitation Scenario

An adversary targeting an organization's computer vision API (e.g., an object detection service for security camera analysis or medical imaging) identifies that the backend uses TensorFlow on GPU. They craft a malformed gRPC or REST inference request to the model's predict endpoint, supplying a scores tensor with rank 3 instead of the required 4. The missing input validation causes the CUDA kernel to receive an unexpected tensor shape, triggering a crash of the GPU-side process. The attacker automates this request at intervals to maintain a persistent denial of service against the inference endpoint, disrupting downstream automated decision systems that depend on the model's output.