{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5O4Y5FYZN6BEHURZGS27J6LQDI","short_pith_number":"pith:5O4Y5FYZ","schema_version":"1.0","canonical_sha256":"ebb98e97196f8243d23934b5f4f9701a30b8538793ab5db533ebc17a42e0ec4d","source":{"kind":"arxiv","id":"2011.14107","version":3},"attestation_state":"computed","paper":{"title":"Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Hui-Po Wang, Mario Fritz, Ning Yu","submitted_at":"2020-11-28T11:07:36Z","abstract_excerpt":"While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation. We show that state-of-the-art GAN models -- such as they are being publicly released by researchers and industry -- can be used for a range of applications beyond unconditional image generation. We achieve this by an iterative scheme that also allows gaining control over the image generation process despite the highly non-linear latent spaces of the latest GAN models. We demonstrate that t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.14107","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-28T11:07:36Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"136291a24e536648232230716cf5ecbd2c3f543e378706cd41e813d0c0f1af33","abstract_canon_sha256":"c4f3564abb9aaef5a9518d3f20debc59ba35da7980f12d80ad4a10a9a464b28f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:49.211593Z","signature_b64":"GyM1/1HceTg2ktWOXMDdVH4qxLYprpumQMx4qNHVi2pHyDzeEXSy2pdH+0E+laELP/dOarXhUTkxgLMPQdbFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebb98e97196f8243d23934b5f4f9701a30b8538793ab5db533ebc17a42e0ec4d","last_reissued_at":"2026-07-05T09:24:49.211014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:49.211014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Hui-Po Wang, Mario Fritz, Ning Yu","submitted_at":"2020-11-28T11:07:36Z","abstract_excerpt":"While Generative Adversarial Networks (GANs) show increasing performance and the level of realism is becoming indistinguishable from natural images, this also comes with high demands on data and computation. We show that state-of-the-art GAN models -- such as they are being publicly released by researchers and industry -- can be used for a range of applications beyond unconditional image generation. We achieve this by an iterative scheme that also allows gaining control over the image generation process despite the highly non-linear latent spaces of the latest GAN models. We demonstrate that t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14107","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.14107/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.14107","created_at":"2026-07-05T09:24:49.211073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14107v3","created_at":"2026-07-05T09:24:49.211073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14107","created_at":"2026-07-05T09:24:49.211073+00:00"},{"alias_kind":"pith_short_12","alias_value":"5O4Y5FYZN6BE","created_at":"2026-07-05T09:24:49.211073+00:00"},{"alias_kind":"pith_short_16","alias_value":"5O4Y5FYZN6BEHURZ","created_at":"2026-07-05T09:24:49.211073+00:00"},{"alias_kind":"pith_short_8","alias_value":"5O4Y5FYZ","created_at":"2026-07-05T09:24:49.211073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20164","citing_title":"StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI","json":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI.json","graph_json":"https://pith.science/api/pith-number/5O4Y5FYZN6BEHURZGS27J6LQDI/graph.json","events_json":"https://pith.science/api/pith-number/5O4Y5FYZN6BEHURZGS27J6LQDI/events.json","paper":"https://pith.science/paper/5O4Y5FYZ"},"agent_actions":{"view_html":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI","download_json":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI.json","view_paper":"https://pith.science/paper/5O4Y5FYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14107&json=true","fetch_graph":"https://pith.science/api/pith-number/5O4Y5FYZN6BEHURZGS27J6LQDI/graph.json","fetch_events":"https://pith.science/api/pith-number/5O4Y5FYZN6BEHURZGS27J6LQDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI/action/storage_attestation","attest_author":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI/action/author_attestation","sign_citation":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI/action/citation_signature","submit_replication":"https://pith.science/pith/5O4Y5FYZN6BEHURZGS27J6LQDI/action/replication_record"}},"created_at":"2026-07-05T09:24:49.211073+00:00","updated_at":"2026-07-05T09:24:49.211073+00:00"}