TY - JOUR AU - Sucholutsky, Ilia AU - Schonlau, Matthias PY - 2021/05/18 Y2 - 2024/03/29 TI - SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract) JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 18 SE - AAAI Student Abstract and Poster Program DO - 10.1609/aaai.v35i18.17945 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17945 SP - 15897-15898 AB - We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations - in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecure channels. ER -