Deep Learning Verification

Train robust image networks and verify image network robustness

Deep learning verification is a set of techniques for assessing the properties of deep neural networks. For example, you can verify the robustness properties of a network, compute network output bounds, and find adversarial examples.

The Deep Learning Toolbox™ Verification Library support package enables testing robustness properties of deep learning networks. Use this library to verify whether a deep learning network is robust against adversarial examples, compute the output bounds for a set of input bounds, and detect out-of-distribution data.

Use the verifyNetworkRobustness function to verify network robustness to adversarial examples. A network is robust to adversarial inputs if the predicted class of the network does not change when the input is perturbed between specified lower and upper input bounds. For a set of input bounds, the function checks if the network is robust to adversarial examples between those input bounds and returns either verified, violated, or unproven.
Use the estimateNetworkOutputBounds function to estimate the range of output values that the network returns when the input is between specified lower and upper bounds. Use this function to estimate how sensitive the network predictions are to input perturbation.
Use the networkDistributionDiscriminator function to create a distribution discriminator that separates data into in- and out-of-distribution.

Funzioni

`estimateNetworkOutputBounds`	Estimate output bounds of deep learning network (Da R2022b)
`verifyNetworkRobustness`	Verify adversarial robustness of deep learning network (Da R2022b)
`networkDistributionDiscriminator`	Deep learning distribution discriminator (Da R2023a)
`isInNetworkDistribution`	Determine whether data is within the distribution of the network (Da R2023a)
`distributionScores`	Distribution confidence scores (Da R2023a)

Argomenti

Verify Robustness of Deep Learning Neural Network
This example shows how to verify the adversarial robustness of a deep learning neural network.
Deep Learning Visualization Methods
Learn about and compare deep learning visualization methods.

Esempi in primo piano

Generate Untargeted and Targeted Adversarial Examples for Image Classification

Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.

Apri live script

Train Image Classification Network Robust to Adversarial Examples

Train a neural network that is robust to adversarial examples using fast gradient sign method (FGSM) adversarial training.

Apri live script

Train Robust Deep Learning Network with Jacobian Regularization

Train a neural network that is robust to adversarial examples using a Jacobian regularization scheme.

Apri live script

Generate Adversarial Examples for Semantic Segmentation

Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).

Apri live script

Explore Semantic Segmentation Network Using Grad-CAM

Explore the predictions of a pretrained semantic segmentation network using Grad-CAM.

Apri live script