DNNV: A Framework for Deep Neural Network Verification

by   David Shriver, et al.

Despite the large number of sophisticated deep neural network (DNN) verification algorithms, DNN verifier developers, users, and researchers still face several challenges. First, verifier developers must contend with the rapidly changing DNN field to support new DNN operations and property types. Second, verifier users have the burden of selecting a verifier input format to specify their problem. Due to the many input formats, this decision can greatly restrict the verifiers that a user may run. Finally, researchers face difficulties in re-using benchmarks to evaluate and compare verifiers, due to the large number of input formats required to run different verifiers. Existing benchmarks are rarely in formats supported by verifiers other than the one for which the benchmark was introduced. In this work we present DNNV, a framework for reducing the burden on DNN verifier researchers, developers, and users. DNNV standardizes input and output formats, includes a simple yet expressive DSL for specifying DNN properties, and provides powerful simplification and reduction operations to facilitate the application, development, and comparison of DNN verifiers. We show how DNNV increases the support of verifiers for existing benchmarks from 30



There are no comments yet.


page 1

page 2

page 3

page 4


Boosting the Robustness Verification of DNN by Identifying the Achilles's Heel

Deep Neural Network (DNN) is a widely used deep learning technique. How ...

Simplifying Neural Networks with the Marabou Verification Engine

Deep neural network (DNN) verification is an emerging field, with divers...

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks

With the rapid development of deep neural networks (DNN), there emerges ...

A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification

We introduce a new attack against face verification systems based on Dee...

Sparse Deep Neural Network Graph Challenge

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches t...

C-3PO: Click-sequence-aware DeeP Neural Network (DNN)-based Pop-uPs RecOmmendation

With the emergence of mobile and wearable devices, push notification bec...

AI Matrix - Synthetic Benchmarks for DNN

Deep neural network (DNN) architectures, such as convolutional neural ne...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.