Vulnerability-Lookup

CVE-2026-44512 (GCVE-0-2026-44512)

Vulnerability from cvelistv5 – Published: 2026-07-08 19:32 – Updated: 2026-07-09 13:36

Title

ONNX: Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)

Summary

Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0.

Severity

5.5 (Medium)


                        
                          CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

SSVC

Exploitation: poc Automatable: no Technical Impact: partial

CISA Coordinator (v2.0.3)

CWE

CWE-476 - NULL Pointer Dereference

Assigner

GitHub_M

References

4 references

URL	Tags
https://github.com/onnx/onnx/security/advisories/…	x_refsource_CONFIRM
https://github.com/onnx/onnx/pull/7813	x_refsource_MISC
https://github.com/onnx/onnx/commit/cd310408165ad…	x_refsource_MISC
https://github.com/onnx/onnx/releases/tag/v1.22.0	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
onnx	onnx	Affected: >= 1.9.0, < 1.22.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44512",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-09T13:36:51.723168Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-09T13:36:58.289Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "onnx",
          "vendor": "onnx",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.9.0, \u003c 1.22.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 5.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-476",
              "description": "CWE-476: NULL Pointer Dereference",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-08T19:32:04.886Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77"
        },
        {
          "name": "https://github.com/onnx/onnx/pull/7813",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/onnx/onnx/pull/7813"
        },
        {
          "name": "https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf"
        },
        {
          "name": "https://github.com/onnx/onnx/releases/tag/v1.22.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/onnx/onnx/releases/tag/v1.22.0"
        }
      ],
      "source": {
        "advisory": "GHSA-hwpq-hmq9-wj77",
        "discovery": "UNKNOWN"
      },
      "title": "ONNX: Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44512",
    "datePublished": "2026-07-08T19:32:04.886Z",
    "dateReserved": "2026-05-06T18:28:20.887Z",
    "dateUpdated": "2026-07-09T13:36:58.289Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44512",
      "date": "2026-07-09",
      "epss": "0.0017",
      "percentile": "0.06661"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-44512\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-07-08T20:16:49.913\",\"lastModified\":\"2026-07-09T15:16:33.993\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"onnx\",\"product\":\"onnx\",\"versions\":[{\"version\":\"\u003e= 1.9.0, \u003c 1.22.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H\",\"baseScore\":5.5,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":3.6}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-07-09T13:36:51.723168Z\",\"id\":\"CVE-2026-44512\",\"options\":[{\"exploitation\":\"poc\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-476\"}]}],\"references\":[{\"url\":\"https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/onnx/onnx/pull/7813\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/onnx/onnx/releases/tag/v1.22.0\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-44512\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-07-09T13:36:51.723168Z\"}}}], \"references\": [{\"url\": \"https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-07-09T13:36:39.371Z\"}}], \"cna\": {\"title\": \"ONNX: Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)\", \"source\": {\"advisory\": \"GHSA-hwpq-hmq9-wj77\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 5.5, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"onnx\", \"product\": \"onnx\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 1.9.0, \u003c 1.22.0\"}]}], \"references\": [{\"url\": \"https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77\", \"name\": \"https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/onnx/onnx/pull/7813\", \"name\": \"https://github.com/onnx/onnx/pull/7813\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf\", \"name\": \"https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/onnx/onnx/releases/tag/v1.22.0\", \"name\": \"https://github.com/onnx/onnx/releases/tag/v1.22.0\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-476\", \"description\": \"CWE-476: NULL Pointer Dereference\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-07-08T19:32:04.886Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-44512\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-07-09T13:36:58.289Z\", \"dateReserved\": \"2026-05-06T18:28:20.887Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-07-08T19:32:04.886Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-44512

Vulnerability from fkie_nvd - Published: 2026-07-08 20:16 - Updated: 2026-07-09 15:16

Severity

5.5 (Medium) - CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf
	security-advisories@github.com	https://github.com/onnx/onnx/pull/7813
	security-advisories@github.com	https://github.com/onnx/onnx/releases/tag/v1.22.0
	security-advisories@github.com	https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "onnx",
          "vendor": "onnx",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.9.0, \u003c 1.22.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h when processing an untrusted model with an Upsample node that has zero inputs, causing an unrecoverable denial of service. This issue is fixed in version 1.22.0."
    }
  ],
  "id": "CVE-2026-44512",
  "lastModified": "2026-07-09T15:16:33.993",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "LOCAL",
          "availabilityImpact": "HIGH",
          "baseScore": 5.5,
          "baseSeverity": "MEDIUM",
          "confidentialityImpact": "NONE",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 1.8,
        "impactScore": 3.6,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-44512",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-07-09T13:36:51.723168Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-07-08T20:16:49.913",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/onnx/onnx/commit/cd310408165ad47c3cd7eb2b86cb5b80aa2e4fdf"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/onnx/onnx/pull/7813"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/onnx/onnx/releases/tag/v1.22.0"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "url": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Received",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-476"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-HWPQ-HMQ9-WJ77

Vulnerability from github – Published: 2026-07-07 13:02 – Updated: 2026-07-07 13:02

Summary

ONNX has Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)

Details

Summary

Null pointer dereference (SIGSEGV) in Upsample_6_7::adapt_upsample_6_7() (onnx/version_converter/adapters/upsample_6_7.h:31) when convert_version() processes a model with an Upsample node that has zero inputs. The adapter accesses node->inputs()[0]->sizes() without checking input count. 107-byte PoC crashes on Release build.

This is the same class of bug as the Cast adapter advisory (separate report) but in a different adapter, different file, and different operator.

Details

The Upsample 6→7 adapter validates attributes but not inputs:

// upsample_6_7.h:20-33
void adapt_upsample_6_7(..., Node* node) const {
    ONNX_ASSERTM(
        node->hasAttribute(width_scale_symbol) && node->hasAttribute(height_scale_symbol),
        "...")  // Attribute check PASSES

    auto width_scale = node->f(width_scale_symbol);
    auto height_scale = node->f(height_scale_symbol);

    auto input_shape = node->inputs()[0]->sizes();
    //                 ^^^^^^^^^^^^^^^^^^^^
    //                 OOB when inputs().size() == 0 → SIGSEGV
}

The PoC has an Upsample node at opset 6 with the required width_scale and height_scale attributes but zero inputs. The attribute assertions pass, then node->inputs()[0] on an empty ArrayRef: - Release builds (NDEBUG): bounds-check assertion compiled out → reads garbage pointer → SIGSEGV - Debug builds: assert(Index < Length) at array_ref.h:159 → SIGABRT

An Upsample node with zero inputs passes graphProtoToGraph() because the import code only resolves input names present in the protobuf.

PoC

import base64
import onnx
from onnx import version_converter

poc_b64 = "CAI6YQo8EgFZIghVcHNhbXBsZSoVCgt3aWR0aF9zY2FsZRUAAABAoAEBKhYKDGhlaWdodF9zY2FsZRUAAABAoAEBEgR0ZXN0YhsKAVkSFgoUCAESEAoCCAEKAggBCgIIBAoCCARCBAoAEAY="

model = onnx.load_from_string(base64.b64decode(poc_b64))

# CRASHES — Upsample_6_7 adapter dereferences empty inputs array
version_converter.convert_version(model, 7)  # SIGSEGV

107-byte PoC. Confirmed SIGSEGV on both onnx 1.21.0 (pip) and 1.22.0 (source build).

Impact

Any application that uses onnx.version_converter.convert_version() on untrusted models is vulnerable. This includes model conversion pipelines and tools that auto-upgrade opset versions for compatibility. The crash is unrecoverable (SIGSEGV).

This vulnerability is part of a systemic pattern across multiple version converter adapters. A full audit of all ~45 adapters was performed as part of the fix; eight adapters were found with the same class of unguarded indexed access (cast_9_8, softmax_12_13, softmax_13_12, upsample_6_7, upsample_9_10, group_normalization_20_21, broadcast_forward_compatibility, upsample_9_8) and all have been fixed in PR #7813.

Severity

5.5 (Medium)


                  
                    CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "onnx"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.9.0"
            },
            {
              "fixed": "1.22.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-44512"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-476"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-07-07T13:02:10Z",
    "nvd_published_at": null,
    "severity": "MODERATE"
  },
  "details": "### Summary\n\nNull pointer dereference (SIGSEGV) in `Upsample_6_7::adapt_upsample_6_7()` (`onnx/version_converter/adapters/upsample_6_7.h:31`) when `convert_version()` processes a model with an Upsample node that has zero inputs. The adapter accesses `node-\u003einputs()[0]-\u003esizes()` without checking input count. 107-byte PoC crashes on Release build.\n\nThis is the same class of bug as the Cast adapter advisory (separate report) but in a different adapter, different file, and different operator.\n\n### Details\n\nThe Upsample 6\u21927 adapter validates attributes but not inputs:\n```cpp\n// upsample_6_7.h:20-33\nvoid adapt_upsample_6_7(..., Node* node) const {\n    ONNX_ASSERTM(\n        node-\u003ehasAttribute(width_scale_symbol) \u0026\u0026 node-\u003ehasAttribute(height_scale_symbol),\n        \"...\")  // Attribute check PASSES\n\n    auto width_scale = node-\u003ef(width_scale_symbol);\n    auto height_scale = node-\u003ef(height_scale_symbol);\n\n    auto input_shape = node-\u003einputs()[0]-\u003esizes();\n    //                 ^^^^^^^^^^^^^^^^^^^^\n    //                 OOB when inputs().size() == 0 \u2192 SIGSEGV\n}\n```\n\nThe PoC has an Upsample node at opset 6 with the required `width_scale` and `height_scale` attributes but zero inputs. The attribute assertions pass, then `node-\u003einputs()[0]` on an empty `ArrayRef`:\n- Release builds (`NDEBUG`): bounds-check assertion compiled out \u2192 reads garbage pointer \u2192 SIGSEGV\n- Debug builds: `assert(Index \u003c Length)` at `array_ref.h:159` \u2192 SIGABRT\n\nAn Upsample node with zero inputs passes `graphProtoToGraph()` because the import code only resolves input names present in the protobuf.\n\n### PoC\n```python\nimport base64\nimport onnx\nfrom onnx import version_converter\n\npoc_b64 = \"CAI6YQo8EgFZIghVcHNhbXBsZSoVCgt3aWR0aF9zY2FsZRUAAABAoAEBKhYKDGhlaWdodF9zY2FsZRUAAABAoAEBEgR0ZXN0YhsKAVkSFgoUCAESEAoCCAEKAggBCgIIBAoCCARCBAoAEAY=\"\n\nmodel = onnx.load_from_string(base64.b64decode(poc_b64))\n\n# CRASHES \u2014 Upsample_6_7 adapter dereferences empty inputs array\nversion_converter.convert_version(model, 7)  # SIGSEGV\n```\n\n107-byte PoC. Confirmed SIGSEGV on both onnx 1.21.0 (pip) and 1.22.0 (source build).\n\n### Impact\n\nAny application that uses `onnx.version_converter.convert_version()` on untrusted models is vulnerable. This includes model conversion pipelines and tools that auto-upgrade opset versions for compatibility. The crash is unrecoverable (SIGSEGV). \n\nThis vulnerability is part of a systemic pattern across multiple version converter adapters. A full audit of all ~45 adapters was performed as part of the fix; eight adapters were found with the same class of unguarded indexed access (cast_9_8, softmax_12_13, softmax_13_12, upsample_6_7, upsample_9_10, group_normalization_20_21, broadcast_forward_compatibility, upsample_9_8) and all have been fixed in PR #7813.",
  "id": "GHSA-hwpq-hmq9-wj77",
  "modified": "2026-07-07T13:02:10Z",
  "published": "2026-07-07T13:02:10Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/onnx/onnx/security/advisories/GHSA-hwpq-hmq9-wj77"
    },
    {
      "type": "WEB",
      "url": "https://github.com/onnx/onnx/pull/7916"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/onnx/onnx"
    },
    {
      "type": "WEB",
      "url": "https://github.com/onnx/onnx/releases/tag/v1.22.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "ONNX has Null Pointer Dereference in Upsample Version Converter Adapter (Zero Inputs)"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

Action not permitted

CVE-2026-44512 (GCVE-0-2026-44512)

FKIE_CVE-2026-44512

GHSA-HWPQ-HMQ9-WJ77

Summary

Details

PoC

Impact

Tags

Sightings

Nomenclature