Dankworth, R., & Schwalbe, G. (2025). Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties.
Style de citation Chicago (17e éd.)Dankworth, Raik, et Gesina Schwalbe. Attack Logics, Not Outputs: Towards Efficient Robustification of Deep Neural Networks by Falsifying Concept-based Properties. 2025.
Style de citation MLA (9e éd.)Dankworth, Raik, et Gesina Schwalbe. Attack Logics, Not Outputs: Towards Efficient Robustification of Deep Neural Networks by Falsifying Concept-based Properties. 2025.
Attention : ces citations peuvent ne pas être correctes à 100%.