CVE-2026-115922
Awaiting Analysis Awaiting Analysis - Queue

Memory Exhaustion in ONNX Tensor Unpacking

Publication date: 2026-10-26

Last updated on: 2026-10-26

Assigner: GitHub, Inc.

Description
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to 1.22.0, _unpack_2bit() and _unpack_4bit() resize unpacked arrays according to attacker-controlled TensorProto.dims without verifying that raw_data or int32_data encodes the declared number of elements. Materializing an untrusted UINT2, INT2, UINT4, INT4, or FLOAT4E2M1 tensor through onnx.numpy_helper.to_array() or onnx.reference.ReferenceEvaluator can therefore expand a small packed payload into a disproportionately large allocation and exhaust memory. This issue is fixed in version 1.22.0.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-10-26
Last Modified
2026-10-26
Generated
2026-10-26
AI Q&A
2026-10-26
EPSS Evaluated
N/A
NVD
CVE-2026-115922
EUVD
EUVD-2026-110049

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
onnx onnx < 1.22.0

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-789 The product allocates memory based on an untrusted, large size value, but it does not ensure that the size is within expected limits, allowing arbitrary amounts of memory to be allocated.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in ONNX before 1.22.0 involves improper handling of tensor dimensions in _unpack_2bit() and _unpack_4bit() functions. Attackers can manipulate TensorProto.dims to force large memory allocations when unpacking small payloads, leading to memory exhaustion during tensor conversion via onnx.numpy_helper.to_array() or onnx.reference.ReferenceEvaluator.

Detection Guidance

This vulnerability can be detected by checking the ONNX version in use. Commands like pip show onnx or pip list | grep onnx can verify if the installed version is below 1.22.0. Additionally, monitor for unexpected memory exhaustion during tensor operations.

Impact Analysis

This flaw could cause denial-of-service by crashing applications or systems due to excessive memory consumption. It may also lead to instability in machine learning pipelines relying on ONNX for tensor operations, potentially disrupting services that depend on these models.

Mitigation Strategies

Upgrade ONNX to version 1.22.0 or later immediately. Avoid using untrusted tensors with onnx.numpy_helper.to_array() or onnx.reference.ReferenceEvaluator until the update is applied. Restrict access to ONNX processing functions to trusted inputs only.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-115922. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart