Search Results for author:
Found 9 papers, 6 papers with code
Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance.
Harnessing Neuron Stability to Improve DNN Verification
We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feedforward networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) applied to the standard MNIST and CIFAR datasets.
PCV: A Point Cloud-Based Network Verifier
Due to complex architecture, dimension of hyper-parameter, and 3D convolution, no verifiers can perform the basic layer-wise verification.
White-box Testing of NLP models with Mask Neuron Coverage
Recent literature has seen growing interest in using black-box strategies like CheckList for testing the behavior of NLP models.
Reducing DNN Properties to Enable Falsification with Adversarial Attacks
Deep Neural Networks (DNN) are increasingly being deployed in safety-critical domains, from autonomous vehicles to medical devices, where the consequences of errors demand techniques that can provide stronger guarantees about behavior than just high test accuracy.
DNNV: A Framework for Deep Neural Network Verification
In this work we present DNNV, a framework for reducing the burden on DNN verifier researchers, developers, and users.
Distribution-Aware Testing of Neural Networks Using Generative Models
Using deep generative model based input validation, we show that all the three techniques generate significant number of invalid test inputs.
Systematic Generation of Diverse Benchmarks for DNN Verification
The field of verification has advanced due to the interplay of theoretical development and empirical evaluation.
Refactoring Neural Networks for Verification
Deep neural networks (DNN) are growing in capability and applicability.
