Denial of Service via crafted untrusted models

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. This vulnerability allows a remote attacker to cause an unrecoverable denial of service (DoS) by providing a specially crafted untrusted model. The flaw occurs when the onnx.version_converter.convert_version() function attempts to process an Upsample node with zero inputs, leading to a null pointer dereference and a system crash. This Moderate impact denial of service flaw in Open Neural Network Exchange (ONNX) can be triggered when processing a specially crafted untrusted model. A remote attacker could exploit this by providing a malicious model with an Upsample node having zero inputs, leading to a null pointer dereference and an unrecoverable system crash. This requires user interaction to process the untrusted model. Red Hat severity: Moderate — CVSS 6.5 (CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H). Weakness: CWE-476. Affected Red Hat products: Red Hat OpenShift AI (RHOAI). Red Hat does not currently list a fixing RHSA for this CVE.