{"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/gifd-a-generative-gradient-inversion-method","title":"GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization","arxiv_id":"2308.04699","date":"2023-08-09","proceeding":"ICCV 2023 1","authors":["Hao Fang","Bin Chen","Xuan Wang","Zhi Wang","Shu-Tao Xia"],"abstract":"Federated Learning (FL) has recently emerged as a promising distributed machine learning framework to preserve clients' privacy, by allowing multiple clients to upload the gradients calculated from their local data to a central server. Recent studies find that the exchanged gradients also take the risk of privacy leakage, e.g., an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. However, performing gradient inversion attacks in the latent space of the GAN model limits their expression ability and generalizability. To tackle these challenges, we propose \\textbf{G}radient \\textbf{I}nversion over \\textbf{F}eature \\textbf{D}omains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers. Instead of optimizing only over the initial latent code, we progressively change the optimized layer, from the initial latent space to intermediate layers closer to the output images. In addition, we design a regularizer to avoid unreal image generation by adding a small ${l_1}$ ball constraint to the searching range. We also extend GIFD to the out-of-distribution (OOD) setting, which weakens the assumption that the training sets of GANs and FL tasks obey the same data distribution. Extensive experiments demonstrate that our method can achieve pixel-level reconstruction and is superior to the existing methods. Notably, GIFD also shows great generalizability under different defense strategy settings and batch sizes.","url_abs":"https://arxiv.org/abs/2308.04699v2","url_pdf":"https://arxiv.org/pdf/2308.04699v2.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":"gifd-a-generative-gradient-inversion-method","repo_url":"https://github.com/ffhibnese/gifd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.04699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04699"}},"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/ffhibnese/gifd","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ffhibnese/GIFD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":4},"by_repo_kind":{"official":{"samples":13,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"1770bad65e763b78","entry":"additive_noise","repo":"ffhibnese/GIFD","repo_kind":"official","path":"defense.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/defense.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1770bad65e763b78"}},{"code_sha256_prefix":"7db01b64f42f28ee","entry":"densenet_cifar","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/nn/densenet.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/nn/densenet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7db01b64f42f28ee"}},{"code_sha256_prefix":"49e3def5d3ba54c9","entry":"gradient_clipping","repo":"ffhibnese/GIFD","repo_kind":"official","path":"defense.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/defense.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49e3def5d3ba54c9"}},{"code_sha256_prefix":"aae188414ae38f51","entry":"gradient_compression","repo":"ffhibnese/GIFD","repo_kind":"official","path":"defense.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/defense.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aae188414ae38f51"}},{"code_sha256_prefix":"21cecdf2721c9a12","entry":"load_config","repo":"ffhibnese/GIFD","repo_kind":"official","path":"rec_mult.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/rec_mult.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21cecdf2721c9a12"}},{"code_sha256_prefix":"2d15f050207aff53","entry":"merge","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/nn/revnet_utils.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/nn/revnet_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d15f050207aff53"}},{"code_sha256_prefix":"24dd50ff238a3c31","entry":"reconstruction_costs","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/reconstruction_algorithms.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/reconstruction_algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"24dd50ff238a3c31"}},{"code_sha256_prefix":"781553d9de1bec97","entry":"split","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/nn/revnet_utils.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/nn/revnet_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"781553d9de1bec97"}},{"code_sha256_prefix":"add5009f628a413f","entry":"training_strategy","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/optimization_strategy.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/optimization_strategy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"add5009f628a413f"}},{"code_sha256_prefix":"e551d62ffffcfda9","entry":"activation_errors","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/metrics.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/metrics.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":"e551d62ffffcfda9"}},{"code_sha256_prefix":"1e0ee02f7f2be4e0","entry":"construct_model","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/nn/models.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/nn/models.py","link_basis":"first_harvest_node","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":"1e0ee02f7f2be4e0"}},{"code_sha256_prefix":"5ef2f520281c0bdf","entry":"psnr","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/metrics.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/metrics.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":"5ef2f520281c0bdf"}},{"code_sha256_prefix":"3d23162c75564e01","entry":"total_variation","repo":"ffhibnese/GIFD","repo_kind":"official","path":"inversefed/metrics.py","file_url":"https://github.com/ffhibnese/GIFD/blob/HEAD/inversefed/metrics.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":"3d23162c75564e01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}