{"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/a-generic-framework-for-privacy-preserving","title":"A generic framework for privacy preserving deep learning","arxiv_id":"1811.04017","date":"2018-11-09","proceeding":null,"authors":["Theo Ryffel","Andrew Trask","Morten Dahl","Bobby Wagner","Jason Mancuso","Daniel Rueckert","Jonathan Passerat-Palmbach"],"abstract":"We detail a new framework for privacy preserving deep learning and discuss\nits assets. The framework puts a premium on ownership and secure processing of\ndata and introduces a valuable representation based on chains of commands and\ntensors. This abstraction allows one to implement complex privacy preserving\nconstructs such as Federated Learning, Secure Multiparty Computation, and\nDifferential Privacy while still exposing a familiar deep learning API to the\nend-user. We report early results on the Boston Housing and Pima Indian\nDiabetes datasets. While the privacy features apart from Differential Privacy\ndo not impact the prediction accuracy, the current implementation of the\nframework introduces a significant overhead in performance, which will be\naddressed at a later stage of the development. We believe this work is an\nimportant milestone introducing the first reliable, general framework for\nprivacy preserving deep learning.","url_abs":"http://arxiv.org/abs/1811.04017v2","url_pdf":"http://arxiv.org/pdf/1811.04017v2.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":"a-generic-framework-for-privacy-preserving","repo_url":"https://github.com/Berenice2018/PySyft-Bc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-generic-framework-for-privacy-preserving","repo_url":"https://github.com/SanaAwan5/transfer_learning_on_mnist_spdz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-generic-framework-for-privacy-preserving","repo_url":"https://github.com/mukira/PySyft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"},{"task_slug":"privacy-preserving-deep-learning","task_name":"Privacy Preserving Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.04017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04017"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Berenice2018/PySyft-Bc","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mukira/PySyft","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SanaAwan5/transfer_learning_on_mnist_spdz","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"12a7f6850c5c9f29","entry":"numpy_tensor_deserializer","repo":"Berenice2018/PySyft-Bc","repo_kind":"listed","path":"syft/serde/torch_serde.py","file_url":"https://github.com/Berenice2018/PySyft-Bc/blob/HEAD/syft/serde/torch_serde.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12a7f6850c5c9f29"}},{"code_sha256_prefix":"99998102ce327cf9","entry":"numpy_tensor_serializer","repo":"Berenice2018/PySyft-Bc","repo_kind":"listed","path":"syft/serde/torch_serde.py","file_url":"https://github.com/Berenice2018/PySyft-Bc/blob/HEAD/syft/serde/torch_serde.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99998102ce327cf9"}},{"code_sha256_prefix":"ad5eca2af374293a","entry":"preprocess_data","repo":"SanaAwan5/transfer_learning_on_mnist_spdz","repo_kind":"listed","path":"dataset.py","file_url":"https://github.com/SanaAwan5/transfer_learning_on_mnist_spdz/blob/HEAD/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad5eca2af374293a"}},{"code_sha256_prefix":"cf1ca8eb225f00e9","entry":"preprocess_data","repo":"SanaAwan5/transfer_learning_on_mnist_spdz","repo_kind":"listed","path":"dataset_emnist.py","file_url":"https://github.com/SanaAwan5/transfer_learning_on_mnist_spdz/blob/HEAD/dataset_emnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf1ca8eb225f00e9"}},{"code_sha256_prefix":"5e390dbfdd2a0fd5","entry":"preprocess_data2","repo":"SanaAwan5/transfer_learning_on_mnist_spdz","repo_kind":"listed","path":"dataset_emnist.py","file_url":"https://github.com/SanaAwan5/transfer_learning_on_mnist_spdz/blob/HEAD/dataset_emnist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e390dbfdd2a0fd5"}},{"code_sha256_prefix":"806045a2dd946b65","entry":"torch_tensor_serializer","repo":"Berenice2018/PySyft-Bc","repo_kind":"listed","path":"syft/serde/torch_serde.py","file_url":"https://github.com/Berenice2018/PySyft-Bc/blob/HEAD/syft/serde/torch_serde.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"806045a2dd946b65"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}