{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/reconstructing-training-data-with-informed","title":"Reconstructing Training Data with Informed Adversaries","arxiv_id":"2201.04845","date":"2022-01-13","proceeding":null,"authors":["Borja Balle","Giovanni Cherubin","Jamie Hayes"],"abstract":"Given access to a machine learning model, can an adversary reconstruct the model's training data? This work studies this question from the lens of a powerful informed adversary who knows all the training data points except one. By instantiating concrete attacks, we show it is feasible to reconstruct the remaining data point in this stringent threat model. For convex models (e.g. logistic regression), reconstruction attacks are simple and can be derived in closed-form. For more general models (e.g. neural networks), we propose an attack strategy based on training a reconstructor network that receives as input the weights of the model under attack and produces as output the target data point. We demonstrate the effectiveness of our attack on image classifiers trained on MNIST and CIFAR-10, and systematically investigate which factors of standard machine learning pipelines affect reconstruction success. Finally, we theoretically investigate what amount of differential privacy suffices to mitigate reconstruction attacks by informed adversaries. Our work provides an effective reconstruction attack that model developers can use to assess memorization of individual points in general settings beyond those considered in previous works (e.g. generative language models or access to training gradients); it shows that standard models have the capacity to store enough information to enable high-fidelity reconstruction of training data points; and it demonstrates that differential privacy can successfully mitigate such attacks in a parameter regime where utility degradation is minimal.","url_abs":"https://arxiv.org/abs/2201.04845v2","url_pdf":"https://arxiv.org/pdf/2201.04845v2.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":"reconstructing-training-data-with-informed","repo_url":"https://github.com/deepmind/informed_adversary_mnist_reconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"reconstructing-training-data-with-informed","repo_url":"https://github.com/facebookresearch/bounding_data_reconstruction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"reconstruction-attack","task_name":"Reconstruction Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.04845","atlas_url":"https://app.syntology.ai/?focus=2201.04845","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2201.04845"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.04845\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.04845"},"call":"get_concepts_for_paper(arxiv_id=\"2201.04845\")"}],"by_repo":[{"repo":"deepmind/informed_adversary_mnist_reconstruction","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/bounding_data_reconstruction","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2201.12383"],"harvested_for_calls":[{"arxiv_id":"2201.12383","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2201.12383"},"call":"get_harvested_code_for_paper(arxiv_id=\"2201.12383\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5a99c3910e0e264cc78cb7265cf7ef8a9601e28bce03f58e612b9c9db31d4705","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}