{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4SG5AVQW3XLE45IT6AMUXUQE53","short_pith_number":"pith:4SG5AVQW","schema_version":"1.0","canonical_sha256":"e48dd05616ddd64e7513f0194bd204eecfcc1e3fa5d6707d0e0073c9b3b7f93d","source":{"kind":"arxiv","id":"2302.14267","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Attack with Raindrops","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Lu, Huilin Xiong, Jiyuan Liu, Mingkang Xiong, Tao Zhang","submitted_at":"2023-02-28T03:01:58Z","abstract_excerpt":"Deep neural networks (DNNs) are known to be vulnerable to adversarial examples, which are usually designed artificially to fool DNNs, but rarely exist in real-world scenarios. In this paper, we study the adversarial examples caused by raindrops, to demonstrate that there exist plenty of natural phenomena being able to work as adversarial attackers to DNNs. Moreover, we present a new approach to generate adversarial raindrops, denoted as AdvRD, using the generative adversarial network (GAN) technique to simulate natural raindrops. The images crafted by our AdvRD look very similar to the real-wo"},"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":"2302.14267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-28T03:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"be9bdbc2e579dea4e751d9b947632d7db986e7df7c5c9d58a8bc48b7a3204d71","abstract_canon_sha256":"08cc33c0aecb66093ec09f872514daf30e82d9c079a29384172a9fe75a10e00b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:09.648678Z","signature_b64":"Xx9m0MqRjbfyOEGn4aN7zra9m+iLhgwIjk2TTbvH2+1jpiUiraR+TyBT+ijBW9RYfmMyrPui0+Zb88OU98buCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e48dd05616ddd64e7513f0194bd204eecfcc1e3fa5d6707d0e0073c9b3b7f93d","last_reissued_at":"2026-07-05T06:31:09.648072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:09.648072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attack with Raindrops","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Lu, Huilin Xiong, Jiyuan Liu, Mingkang Xiong, Tao Zhang","submitted_at":"2023-02-28T03:01:58Z","abstract_excerpt":"Deep neural networks (DNNs) are known to be vulnerable to adversarial examples, which are usually designed artificially to fool DNNs, but rarely exist in real-world scenarios. In this paper, we study the adversarial examples caused by raindrops, to demonstrate that there exist plenty of natural phenomena being able to work as adversarial attackers to DNNs. Moreover, we present a new approach to generate adversarial raindrops, denoted as AdvRD, using the generative adversarial network (GAN) technique to simulate natural raindrops. The images crafted by our AdvRD look very similar to the real-wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14267","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/2302.14267/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":"2302.14267","created_at":"2026-07-05T06:31:09.648148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14267v2","created_at":"2026-07-05T06:31:09.648148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14267","created_at":"2026-07-05T06:31:09.648148+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SG5AVQW3XLE","created_at":"2026-07-05T06:31:09.648148+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SG5AVQW3XLE45IT","created_at":"2026-07-05T06:31:09.648148+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SG5AVQW","created_at":"2026-07-05T06:31:09.648148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18776","citing_title":"Fall Leaf Adversarial Attack on Traffic Sign Classification","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53","json":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53.json","graph_json":"https://pith.science/api/pith-number/4SG5AVQW3XLE45IT6AMUXUQE53/graph.json","events_json":"https://pith.science/api/pith-number/4SG5AVQW3XLE45IT6AMUXUQE53/events.json","paper":"https://pith.science/paper/4SG5AVQW"},"agent_actions":{"view_html":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53","download_json":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53.json","view_paper":"https://pith.science/paper/4SG5AVQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14267&json=true","fetch_graph":"https://pith.science/api/pith-number/4SG5AVQW3XLE45IT6AMUXUQE53/graph.json","fetch_events":"https://pith.science/api/pith-number/4SG5AVQW3XLE45IT6AMUXUQE53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53/action/storage_attestation","attest_author":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53/action/author_attestation","sign_citation":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53/action/citation_signature","submit_replication":"https://pith.science/pith/4SG5AVQW3XLE45IT6AMUXUQE53/action/replication_record"}},"created_at":"2026-07-05T06:31:09.648148+00:00","updated_at":"2026-07-05T06:31:09.648148+00:00"}