{"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/embedding-watermarks-into-deep-neural","title":"Embedding Watermarks into Deep Neural Networks","arxiv_id":"1701.04082","date":"2017-01-15","proceeding":null,"authors":["Yusuke Uchida","Yuki Nagai","Shigeyuki Sakazawa","Shin'ichi Satoh"],"abstract":"Deep neural networks have recently achieved significant progress. Sharing\ntrained models of these deep neural networks is very important in the rapid\nprogress of researching or developing deep neural network systems. At the same\ntime, it is necessary to protect the rights of shared trained models. To this\nend, we propose to use a digital watermarking technology to protect\nintellectual property or detect intellectual property infringement of trained\nmodels. Firstly, we formulate a new problem: embedding watermarks into deep\nneural networks. We also define requirements, embedding situations, and attack\ntypes for watermarking to deep neural networks. Secondly, we propose a general\nframework to embed a watermark into model parameters using a parameter\nregularizer. Our approach does not hurt the performance of networks into which\na watermark is embedded. Finally, we perform comprehensive experiments to\nreveal the potential of watermarking to deep neural networks as a basis of this\nnew problem. We show that our framework can embed a watermark in the situations\nof training a network from scratch, fine-tuning, and distilling without hurting\nthe performance of a deep neural network. The embedded watermark does not\ndisappear even after fine-tuning or parameter pruning; the watermark completely\nremains even after removing 65% of parameters were pruned. The implementation\nof this research is: https://github.com/yu4u/dnn-watermark","url_abs":"http://arxiv.org/abs/1701.04082v2","url_pdf":"http://arxiv.org/pdf/1701.04082v2.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":"embedding-watermarks-into-deep-neural","repo_url":"https://github.com/yu4u/dnn-watermark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.04082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.04082"}},"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/yu4u/dnn-watermark","reach":null}],"summary":{"ran_honours":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"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":4,"samples":[{"code_sha256_prefix":"f74210f1ce0a6725","entry":"get_param_from_name","repo":"yu4u/dnn-watermark","repo_kind":"official","path":"utility/wmark_validate.py","file_url":"https://github.com/yu4u/dnn-watermark/blob/HEAD/utility/wmark_validate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f74210f1ce0a6725"}},{"code_sha256_prefix":"4cab2a822fbcde8c","entry":"schedule","repo":"yu4u/dnn-watermark","repo_kind":"official","path":"train_wrn.py","file_url":"https://github.com/yu4u/dnn-watermark/blob/HEAD/train_wrn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4cab2a822fbcde8c"}},{"code_sha256_prefix":"61d23f0d22eb9a07","entry":"get_layer_weights_and_predicted","repo":"yu4u/dnn-watermark","repo_kind":"official","path":"utility/wmark_validate.py","file_url":"https://github.com/yu4u/dnn-watermark/blob/HEAD/utility/wmark_validate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61d23f0d22eb9a07"}},{"code_sha256_prefix":"953378d8b55f6ba9","entry":"get_model","repo":"yu4u/dnn-watermark","repo_kind":"official","path":"utility/wmark_validate.py","file_url":"https://github.com/yu4u/dnn-watermark/blob/HEAD/utility/wmark_validate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"953378d8b55f6ba9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}