Search Results for author:
Found 2 papers, 0 papers with code
ADVREPAIR:Provable Repair of Adversarial Attack
Existing neuron-level methods using limited data lack efficacy in fixing adversaries due to the inherent complexity of adversarial attack mechanisms, while adversarial training, leveraging a large number of adversarial samples to enhance robustness, lacks provability.
Incremental Satisfiability Modulo Theory for Verification of Deep Neural Networks
Moreover, based on the framework, we propose the multi-objective DNN repair problem and give an algorithm based on our incremental SMT solving algorithm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
