Deep Learning Toolbox Verification Library

Verify and test robustness of deep learning networks
Updated 14 May 2024
Deep Learning Toolbox Verification Library enables testing robustness properties of deep learning networks.
Use this library to:
  • Verify network robustness to adversarial examples (Since R2022b)
  • Estimate how sensitive the network predictions are to input perturbation (Since R2022b)
  • Explain object detection network predictions using D-RISE (Since R2024a)
  • Create a distribution discriminator that separates data into in- and out-of-distribution (Since R2023a)
  • Detect out-of-distribution (ODD) data in neural networks (Since R2023a)
  • Generate C/C++ and CUDA code for out-of-distribution (runtime monitoring) (Since R2023a)
If you have download or installation problems, please contact Technical Support:
MATLAB Release Compatibility
Created with R2022b
Compatible with R2022b to R2024a
Platform Compatibility
Windows macOS (Apple silicon) macOS (Intel) Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!