Deep Learning Toolbox Verification Library

Verify and test robustness of deep learning networks

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)

Please refer to the documentation here: https://www.mathworks.com/help/deeplearning/verification.html

If you have download or installation problems, please contact Technical Support: https://www.mathworks.com/support/contact_us.html