{"url":"/task/image-classification-with-dp","name":"Image Classification with Differential Privacy","slug":"image-classification-with-dp","description_markdown":"**Image Classification with Differential Privacy** is an improved version of the image classification task whereby the final classification output only describe the patterns of groups within the dataset while withholding information about individuals in the dataset.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":8,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/image-classification-with-dp-on-imagenet","slug":"image-classification-with-dp-on-imagenet","dataset":"ImageNet","dataset_url":"/dataset/imagenet","rows_in_archive":4,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"NFResnet-50","paper_title":"TAN Without a Burn: Scaling Laws of DP-SGD","paper_url":"/paper/tan-without-a-burn-scaling-laws-of-dp-sgd","paper_date":"2022-10-07","arxiv_id":"2210.03403","code_links":[{"title":"facebookresearch/tan","url":"https://github.com/facebookresearch/tan"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":8}}}],"datasets":[{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430}],"subtasks":[],"parent_tasks":[{"url":"/task/image-classification","name":"Image Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":8,"of":8,"tagged_in_all":8,"items":[{"url":"/paper/unlocking-high-accuracy-differentially","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","date":"2022-04-28","arxiv_id":"2204.13650","repositories_listed":3,"syntology":null},{"url":"/paper/private-fair-and-accurate-training-large","title":"Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging","date":"2023-02-03","arxiv_id":"2302.01622","repositories_listed":2,"syntology":null},{"url":"/paper/in-distribution-public-data-synthesis-with","title":"In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/preserving-privacy-in-domain-transfer-of","title":"Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy","date":"2023-06-10","arxiv_id":"2306.06503","repositories_listed":1,"syntology":null},{"url":"/paper/equivariant-differentially-private-deep","title":"Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models","date":"2023-01-30","arxiv_id":"2301.13104","repositories_listed":1,"syntology":null},{"url":"/paper/tan-without-a-burn-scaling-laws-of-dp-sgd","title":"TAN Without a Burn: Scaling Laws of DP-SGD","date":"2022-10-07","arxiv_id":"2210.03403","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":8}},{"url":"/paper/smoothnets-optimizing-cnn-architecture-design","title":"SmoothNets: Optimizing CNN architecture design for differentially private deep learning","date":"2022-05-09","arxiv_id":"2205.04095","repositories_listed":1,"syntology":null},{"url":"/paper/toward-training-at-imagenet-scale-with","title":"Toward Training at ImageNet Scale with Differential Privacy","date":"2022-01-28","arxiv_id":"2201.12328","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}