{"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/manipulating-feature-visualizations-with","title":"Manipulating Feature Visualizations with Gradient Slingshots","arxiv_id":"2401.06122","date":"2024-01-11","proceeding":null,"authors":["Dilyara Bareeva","Marina M. -C. Höhne","Alexander Warnecke","Lukas Pirch","Klaus-Robert Müller","Konrad Rieck","Kirill Bykov"],"abstract":"Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown. A common method used to explain the concepts learned by DNNs is Feature Visualization (FV), which generates a synthetic input signal that maximally activates a particular neuron in the network. In this paper, we investigate the vulnerability of this approach to adversarial model manipulations and introduce a novel method for manipulating FV without significantly impacting the model's decision-making process. The key distinction of our proposed approach is that it does not alter the model architecture. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons by masking the original explanations of neurons with chosen target explanations during model auditing.","url_abs":"https://arxiv.org/abs/2401.06122v2","url_pdf":"https://arxiv.org/pdf/2401.06122v2.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":"manipulating-feature-visualizations-with","repo_url":"https://github.com/dilyabareeva/grad-slingshot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.06122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06122"}},"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":"deterministic:regex_extraction","url":"https://github.com/dilyabareeva/grad-slingshot","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":12,"unverified":6},"by_repo_kind":{"official":{"samples":18,"ran":12,"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":"fdbaf0d0cb186b10","entry":"act_max_top_k_from_dataset","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"plotting.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/plotting.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":"fdbaf0d0cb186b10"}},{"code_sha256_prefix":"6dddfa6475cdc440","entry":"activation_max_top_k","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"plotting.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/plotting.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":"6dddfa6475cdc440"}},{"code_sha256_prefix":"cb99d67a4a505067","entry":"get_nested_attr","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/forward_hook.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/forward_hook.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":"cb99d67a4a505067"}},{"code_sha256_prefix":"31aae0b81729befe","entry":"imagenet_dream","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/fv_transforms.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/fv_transforms.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":"31aae0b81729befe"}},{"code_sha256_prefix":"610e532eeeafa90c","entry":"load_image_net_data","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"data_loader.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/data_loader.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":"610e532eeeafa90c"}},{"code_sha256_prefix":"b834e29a85d15c71","entry":"make_layers","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"models.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/models.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":"b834e29a85d15c71"}},{"code_sha256_prefix":"d5da8ca746a0cf9b","entry":"one_d_collate_fn","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/manipulation_set.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/manipulation_set.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":"d5da8ca746a0cf9b"}},{"code_sha256_prefix":"3e2ee5b40f872f43","entry":"preservation_loss","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/loss.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/loss.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":"3e2ee5b40f872f43"}},{"code_sha256_prefix":"3ae37e854aa2fc88","entry":"preservation_loss_prox_pulse_ce","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/loss.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/loss.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":"3ae37e854aa2fc88"}},{"code_sha256_prefix":"86aefbf00edf3f75","entry":"read_target_image","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/utils.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/utils.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":"86aefbf00edf3f75"}},{"code_sha256_prefix":"bdbfcdaff4df9f8e","entry":"resize_transform","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/fv_transforms.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/fv_transforms.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":"bdbfcdaff4df9f8e"}},{"code_sha256_prefix":"60f19087598c4668","entry":"vit_cls_token_target_direction","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/target_activations.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/target_activations.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":"60f19087598c4668"}},{"code_sha256_prefix":"95db6492f04d7140","entry":"fcfgs","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"models.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/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":"95db6492f04d7140"}},{"code_sha256_prefix":"20528158cd3429d4","entry":"load_cifar_data","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"data_loader.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/data_loader.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":"20528158cd3429d4"}},{"code_sha256_prefix":"f0c45d4ecbd11674","entry":"load_mnist_data","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"data_loader.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/data_loader.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":"f0c45d4ecbd11674"}},{"code_sha256_prefix":"d37c77213d240c9c","entry":"manipulation_loss_grad_based","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/loss.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/loss.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":"d37c77213d240c9c"}},{"code_sha256_prefix":"1ba3884299b9ff1c","entry":"modified_vgg","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"models.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/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":"1ba3884299b9ff1c"}},{"code_sha256_prefix":"6e281e5c8b321a96","entry":"vit_transforms","repo":"dilyabareeva/grad-slingshot","repo_kind":"official","path":"core/fv_transforms.py","file_url":"https://github.com/dilyabareeva/grad-slingshot/blob/HEAD/core/fv_transforms.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":"6e281e5c8b321a96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}