The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

1 code implementation • 3 Apr 2024 • Stephen Casper, Jieun Yun, Joonhyuk Baek, Yeseong Jung, Minhwan Kim, Kiwan Kwon, Saerom Park, Hayden Moore, David Shriver, Marissa Connor, Keltin Grimes, Angus Nicolson, Arush Tagade, Jessica Rumbelow, Hieu Minh Nguyen, Dylan Hadfield-Menell

Interpretability techniques are valuable for helping humans understand and oversee AI systems.

Reducing DNN Properties to Enable Falsification with Adversarial Attacks

1 code implementation • IEEE/ACM 43rd International Conference on Software Engineering (ICSE) 2021 • David Shriver, Sebastian Elbaum, Matthew B. Dwyer

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.

Adversarial Attack Autonomous Vehicles

DNNV: A Framework for Deep Neural Network Verification

1 code implementation • 26 May 2021 • David Shriver, Sebastian Elbaum, Matthew B. Dwyer

In this work we present DNNV, a framework for reducing the burden on DNN verifier researchers, developers, and users.

Systematic Generation of Diverse Benchmarks for DNN Verification

1 code implementation • 14 Jul 2020 • Dong Xu, David Shriver, Matthew B. Dwyer, Sebastian Elbaum

The field of verification has advanced due to the interplay of theoretical development and empirical evaluation.

Refactoring Neural Networks for Verification

2 code implementations • 6 Aug 2019 • David Shriver, Dong Xu, Sebastian Elbaum, Matthew B. Dwyer

Deep neural networks (DNN) are growing in capability and applicability.