{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/secdd-efficient-and-secure-method-for","title":"SecDD: Efficient and Secure Method for Remotely Training Neural Networks","arxiv_id":"2009.09155","date":"2020-09-19","proceeding":null,"authors":["Ilia Sucholutsky","Matthias Schonlau"],"abstract":"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 unsecured channels.","url_abs":"https://arxiv.org/abs/2009.09155v1","url_pdf":"https://arxiv.org/pdf/2009.09155v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"secdd-efficient-and-secure-method-for","repo_url":"https://github.com/ilia10000/dataset-distillation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.09155","atlas_url":"https://app.syntology.ai/?focus=2009.09155","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}