{"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/idlg-improved-deep-leakage-from-gradients","title":"iDLG: Improved Deep Leakage from Gradients","arxiv_id":"2001.02610","date":"2020-01-08","proceeding":null,"authors":["Bo Zhao","Konda Reddy Mopuri","Hakan Bilen"],"abstract":"It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their Deep Leakage from Gradient (DLG) method, they synthesize the dummy data and corresponding labels with the supervision of shared gradients. However, DLG has difficulty in convergence and discovering the ground-truth labels consistently. In this paper, we find that sharing gradients definitely leaks the ground-truth labels. We propose a simple but reliable approach to extract accurate data from the gradients. Particularly, our approach can certainly extract the ground-truth labels as opposed to DLG, hence we name it Improved DLG (iDLG). Our approach is valid for any differentiable model trained with cross-entropy loss over one-hot labels. We mathematically illustrate how our method can extract ground-truth labels from the gradients and empirically demonstrate the advantages over DLG.","url_abs":"https://arxiv.org/abs/2001.02610v1","url_pdf":"https://arxiv.org/pdf/2001.02610v1.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":"idlg-improved-deep-leakage-from-gradients","repo_url":"https://github.com/PatrickZH/Improved-Deep-Leakage-from-Gradients","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"idlg-improved-deep-leakage-from-gradients","repo_url":"https://github.com/Koukyosyumei/AIJack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"idlg-improved-deep-leakage-from-gradients","repo_url":"https://github.com/Mishuni/ViT_Inversion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"idlg-improved-deep-leakage-from-gradients","repo_url":"https://github.com/hangyuzhu/leakage-attack-in-federated-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.02610","atlas_url":"https://app.syntology.ai/?focus=2001.02610","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":"2001.02610"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2001.02610\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2001.02610"},"call":"get_concepts_for_paper(arxiv_id=\"2001.02610\")"}],"by_repo":[{"repo":"PatrickZH/Improved-Deep-Leakage-from-Gradients","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Koukyosyumei/AIJack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["1812.06127","2102.08504","2104.07586"],"harvested_for_calls":[{"arxiv_id":"1812.06127","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.06127"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.06127\")"},{"arxiv_id":"2102.08504","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.08504"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.08504\")"},{"arxiv_id":"2104.07586","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.07586"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.07586\")"}]},{"repo":"Mishuni/ViT_Inversion","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"hangyuzhu/leakage-attack-in-federated-learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"1d209906aa3138efb0f0c6280de4477b35a3167bb4a789a5989be6a374c6ba55","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}