CVE-2026-122189
Deferred Deferred - Pending Action

Out-of-Bounds Read in OpenPPL ppl.nn CUDA Optimizer

Vulnerability report for CVE-2026-122189, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-11-05

Last updated on: 2026-11-05

Assigner: VulDB

Description

A vulnerability has been found in OpenPPL ppl.nn up to bb84dc9952809b3a5a0036858a3d9f68af1c83d5. The affected element is the function OptGraph::InitQuantization of the file src/ppl/nn/engines/cuda/optimizer/opt_graph.cc of the component CUDA Optimizer. Such manipulation of the argument per_channel/bit_width/tensor_max/tensor_min/scale leads to out-of-bounds read. The attack can be launched remotely. The exploit has been disclosed to the public and may be used. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-11-05
Last Modified
2026-11-05
Generated
2026-11-06
AI Q&A
2026-11-05
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
OpenPPL ppl.nn bb84dc9952809b3a5a0036858a3d9f68af1c83d5

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-125 The product reads data past the end, or before the beginning, of the intended buffer.
CWE-119 The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is a heap-buffer-overflow in the OpenPPL ppl.nn library's CUDA Optimizer component. It occurs in the OptGraph::InitQuantization function when processing a quant.json file with missing keys like per_channel, bit_width, tensor_max, tensor_min, or scale. The function fails to validate these inputs, leading to out-of-bounds memory reads during graph optimization.

Detection Guidance

To detect this vulnerability, monitor for crashes in the CUDA Optimizer component of ppl.nn when processing quant.json files. Use AddressSanitizer to detect heap-buffer-overflow errors during graph optimization. Check for missing keys in tensor entries like per_channel, bit_width, tensor_max, tensor_min, and scale.

Impact Analysis

An attacker could exploit this to cause crashes or execute arbitrary code on systems using the affected ppl.nn library. Since the attack can be launched remotely, it poses a risk to servers or applications processing malformed quant.json files. The exploit may lead to denial-of-service or potential data leaks depending on the system's memory layout.

Compliance Impact

This vulnerability could impact compliance by enabling unauthorized data access or system disruption. GDPR requires protecting personal data; a breach could lead to violations. HIPAA mandates safeguarding health data; crashes or code execution may compromise confidentiality. Organizations must address this to avoid regulatory penalties and reputational damage.

Mitigation Strategies

Immediately validate all inner map lookups in quant.json files for required keys. Ensure tensor_min and tensor_max have equal lengths before processing. Avoid using untrusted quant.json files. Update to a patched version of ppl.nn once available.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-122189. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart

Security Radar

News mentioning this vulnerability
Loading related security news...