{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WU2Q46T42H24JQNGB7PRZN6QSU","short_pith_number":"pith:WU2Q46T4","schema_version":"1.0","canonical_sha256":"b5350e7a7cd1f5c4c1a60fdf1cb7d0952668bc2eda67fb22968e48a8aaed03f3","source":{"kind":"arxiv","id":"1812.00552","version":2},"attestation_state":"computed","paper":{"title":"Universal Perturbation Attack Against Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hong Liu, Jie Li, Qi Tian, Rongrong Ji, Xiaopeng Hong, Yue Gao","submitted_at":"2018-12-03T04:52:06Z","abstract_excerpt":"Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has been paid to attacking image retrieval systems. In this paper, we make the first attempt in attacking image retrieval systems. Concretely, image retrieval attack is to make the retrieval system return irrelevant images to the query at the top ranking list. It plays an important role to corrupt the n"},"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":"1812.00552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-03T04:52:06Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"aea228d63451dc2376cac7d886ae87415f69b923fb49a81b3cc95d38545beb5f","abstract_canon_sha256":"92835f8346f474ee61ab2be619e959be7784407631b1d5f43eaeb3ad35e8bed3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:54.882715Z","signature_b64":"W3N45XkP2eqX2ktKaELhFlD9O2gUShiyTwb6cNOVl5htQvDvuvnb5RG6RQvSrvo9Gg5+zu9QNO2OqyQJBHDUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5350e7a7cd1f5c4c1a60fdf1cb7d0952668bc2eda67fb22968e48a8aaed03f3","last_reissued_at":"2026-07-05T00:03:54.882232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:54.882232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Perturbation Attack Against Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hong Liu, Jie Li, Qi Tian, Rongrong Ji, Xiaopeng Hong, Yue Gao","submitted_at":"2018-12-03T04:52:06Z","abstract_excerpt":"Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has been paid to attacking image retrieval systems. In this paper, we make the first attempt in attacking image retrieval systems. Concretely, image retrieval attack is to make the retrieval system return irrelevant images to the query at the top ranking list. It plays an important role to corrupt the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00552","kind":"arxiv","version":2},"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/1812.00552/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":"1812.00552","created_at":"2026-07-05T00:03:54.882290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00552v2","created_at":"2026-07-05T00:03:54.882290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00552","created_at":"2026-07-05T00:03:54.882290+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU2Q46T42H24","created_at":"2026-07-05T00:03:54.882290+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU2Q46T42H24JQNG","created_at":"2026-07-05T00:03:54.882290+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU2Q46T4","created_at":"2026-07-05T00:03:54.882290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU","json":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU.json","graph_json":"https://pith.science/api/pith-number/WU2Q46T42H24JQNGB7PRZN6QSU/graph.json","events_json":"https://pith.science/api/pith-number/WU2Q46T42H24JQNGB7PRZN6QSU/events.json","paper":"https://pith.science/paper/WU2Q46T4"},"agent_actions":{"view_html":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU","download_json":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU.json","view_paper":"https://pith.science/paper/WU2Q46T4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00552&json=true","fetch_graph":"https://pith.science/api/pith-number/WU2Q46T42H24JQNGB7PRZN6QSU/graph.json","fetch_events":"https://pith.science/api/pith-number/WU2Q46T42H24JQNGB7PRZN6QSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU/action/storage_attestation","attest_author":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU/action/author_attestation","sign_citation":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU/action/citation_signature","submit_replication":"https://pith.science/pith/WU2Q46T42H24JQNGB7PRZN6QSU/action/replication_record"}},"created_at":"2026-07-05T00:03:54.882290+00:00","updated_at":"2026-07-05T00:03:54.882290+00:00"}