CVE-2026-68991: Samsung Exynos memory corruption in NeuralNetworks HAL

CVE-2026-68991 · Severity: info · Published 2026-11-05

The Samsung Exynos processor's neural network processing component fails to validate input data properly, allowing memory corruption that can cause system crashes. This affects devices using Exynos chips, potentially disrupting their operation until reboot.

Vendors: Samsung.

Quick answers

Is CVE-2026-68991 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-68991 being exploited in the wild.
How severe is CVE-2026-68991?
Informational severity, published 5 November 2026.
Which products and versions are affected?
Samsung Exynos NeuralNetworks HAL.
Is there a fix for CVE-2026-68991?
No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
How is CVE-2026-68991 attacked?
It is attacked with local access, in device firmware.
Am I affected by CVE-2026-68991?
Check whether you run Samsung Exynos NeuralNetworks HAL. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

Technical details

Improper input validation in the Exynos ENN (Exynos Neural Networks) NeuralNetworks Hardware Abstraction Layer permits memory corruption during request processing. The vulnerability can be triggered locally through the HAL interface and results in denial of service via system crash or instability.

Affected products

  • Samsung Exynos NeuralNetworks HAL

Timeline

  • 2026-11-05: disclosed

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.