{"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/hidden-hiding-data-with-deep-networks","title":"HiDDeN: Hiding Data With Deep Networks","arxiv_id":"1807.09937","date":"2018-07-26","proceeding":"ECCV 2018 9","authors":["Jiren Zhu","Russell Kaplan","Justin Johnson","Li Fei-Fei"],"abstract":"Recent work has shown that deep neural networks are highly sensitive to tiny\nperturbations of input images, giving rise to adversarial examples. Though this\nproperty is usually considered a weakness of learned models, we explore whether\nit can be beneficial. We find that neural networks can learn to use invisible\nperturbations to encode a rich amount of useful information. In fact, one can\nexploit this capability for the task of data hiding. We jointly train encoder\nand decoder networks, where given an input message and cover image, the encoder\nproduces a visually indistinguishable encoded image, from which the decoder can\nrecover the original message. We show that these encodings are competitive with\nexisting data hiding algorithms, and further that they can be made robust to\nnoise: our models learn to reconstruct hidden information in an encoded image\ndespite the presence of Gaussian blurring, pixel-wise dropout, cropping, and\nJPEG compression. Even though JPEG is non-differentiable, we show that a robust\nmodel can be trained using differentiable approximations. Finally, we\ndemonstrate that adversarial training improves the visual quality of encoded\nimages.","url_abs":"http://arxiv.org/abs/1807.09937v1","url_pdf":"http://arxiv.org/pdf/1807.09937v1.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":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/ando-khachatryan/HiDDeN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/antigonerandy/siren","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/cuteyyt/ImageSteganography","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/dungpham98/Hidden_Blocking_Artifact_Reduction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/dungpham98/Hidden_Mismatch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/jirenz/HiDDeN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hidden-hiding-data-with-deep-networks","repo_url":"https://github.com/zhaow32/HiDDeN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.09937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09937"}},"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/ando-khachatryan/HiDDeN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dungpham98/Hidden_Blocking_Artifact_Reduction","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/antigonerandy/siren","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cuteyyt/ImageSteganography","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dungpham98/Hidden_Mismatch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jirenz/HiDDeN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhaow32/HiDDeN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"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":"60fd8f53409daa97","entry":"blocking_value","repo":"dungpham98/Hidden_Blocking_Artifact_Reduction","repo_kind":"listed","path":"blocking_calculation.py","file_url":"https://github.com/dungpham98/Hidden_Blocking_Artifact_Reduction/blob/HEAD/blocking_calculation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60fd8f53409daa97"}},{"code_sha256_prefix":"6dd98b0c20170513","entry":"get_random_rectangle_inside","repo":"ando-khachatryan/HiDDeN","repo_kind":"listed","path":"noise_layers/crop.py","file_url":"https://github.com/ando-khachatryan/HiDDeN/blob/HEAD/noise_layers/crop.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dd98b0c20170513"}},{"code_sha256_prefix":"da226f72e51ba9e6","entry":"parse_pair","repo":"ando-khachatryan/HiDDeN","repo_kind":"listed","path":"noise_argparser.py","file_url":"https://github.com/ando-khachatryan/HiDDeN/blob/HEAD/noise_argparser.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da226f72e51ba9e6"}},{"code_sha256_prefix":"d87db75c2765498f","entry":"random_float","repo":"ando-khachatryan/HiDDeN","repo_kind":"listed","path":"noise_layers/crop.py","file_url":"https://github.com/ando-khachatryan/HiDDeN/blob/HEAD/noise_layers/crop.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d87db75c2765498f"}},{"code_sha256_prefix":"4cb7480b48bada32","entry":"weighted_mse_loss","repo":"dungpham98/Hidden_Blocking_Artifact_Reduction","repo_kind":"listed","path":"model/hidden.py","file_url":"https://github.com/dungpham98/Hidden_Blocking_Artifact_Reduction/blob/HEAD/model/hidden.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb7480b48bada32"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}