Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-63632— ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape

Quick assessment

Affected
onnx onnx
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

ONNX是ONNX组织开源的一个机器学习互操作性的开放标准。 ONNX 1.3.0版本至1.22.0之前版本存在缓冲区错误漏洞，该漏洞源于Gemm_7_6::adapt_gemm_7_6函数在输入张量维度少于二维时缺少秩检查，导致越界读取，可能在opset 7到6降级期间导致进程崩溃。

CVSS 3.3 · Low EPSS 0.17% · P6

Possible ATT&CK Techniques 1 AI

T1496 · Resource Hijacking

Affected Version Matrix 1

VendorProduct Version RangeStatus
onnx onnx >= 1.3.0, < 1.22.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-63632

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
ONNX: Heap-Buffer-Overflow READ in Gemm Version Converter Adapter via Undersized Input Shape
Source: CVE Program / CVE List V5
Vulnerability Description
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.3.0 until 1.22.0, onnx.version_converter.convert_version() can perform an out-of-bounds read in Gemm_7_6::adapt_gemm_7_6() in onnx/version_converter/adapters/gemm_7_6.h when a Gemm node has input tensors with fewer than two dimensions because B_shape[1], A_shape[0], or A_shape[1] is accessed without a rank check, potentially causing a process crash during an opset 7 to 6 downgrade. This issue is fixed in version 1.22.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
跨界内存读
Source: CVE Program / CVE List V5
Vulnerability Title
ONNX 缓冲区错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
ONNX是ONNX组织开源的一个机器学习互操作性的开放标准。 ONNX 1.3.0版本至1.22.0之前版本存在缓冲区错误漏洞，该漏洞源于Gemm_7_6::adapt_gemm_7_6函数在输入张量维度少于二维时缺少秩检查，导致越界读取，可能在opset 7到6降级期间导致进程崩溃。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
onnx onnx >= 1.3.0, < 1.22.0 -

II. Public POCs for CVE-2026-63632

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-63632

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-63632 (2)

Vendor Advisories for CVE-2026-63632 (1)

Vendor Pages for CVE-2026-63632 (1)

IV. Related Vulnerabilities

Same product: onnx
Same vendor: onnx
Same weakness: CWE-125

V. Comments for CVE-2026-63632

No comments yet

Leave a comment