{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UCWQLY6YCEXS35XPW5JAQNMQIR","short_pith_number":"pith:UCWQLY6Y","schema_version":"1.0","canonical_sha256":"a0ad05e3d8112f2df6efb752083590445525fdbc952fd919e65bf74606455113","source":{"kind":"arxiv","id":"1903.03029","version":3},"attestation_state":"computed","paper":{"title":"Attack Type Agnostic Perceptual Enhancement of Adversarial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alptekin Temizel, Bilgin Aksoy","submitted_at":"2019-03-07T16:35:03Z","abstract_excerpt":"Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced during the adversarial image generation process degrades the perceptual quality and introduces artificial colours; making it also difficult for humans to classify images and recognise objects. In this letter, we propose a method to enhance the perceptual quality of these adversarial images. The proposed method is attack type agnostic and could be used in associ"},"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":"1903.03029","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-07T16:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"5ea73d5be9d600f0d2995f29fcb8a354b3d47cd2f0b3e3f88a0f96e29720158a","abstract_canon_sha256":"7870531bdd48aaed5d33a4011cdce05399e847920e1920c2765053bf18a119d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:35.819132Z","signature_b64":"xBjrORm+EYD7yhgJTtupVG3ue6FgGcsHOzDz/IVqMuc6bM6xvlvI7nontAPFh7fI8YN+3UMABIZDHBYWt/TaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0ad05e3d8112f2df6efb752083590445525fdbc952fd919e65bf74606455113","last_reissued_at":"2026-05-17T23:46:35.818625Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:35.818625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attack Type Agnostic Perceptual Enhancement of Adversarial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alptekin Temizel, Bilgin Aksoy","submitted_at":"2019-03-07T16:35:03Z","abstract_excerpt":"Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced during the adversarial image generation process degrades the perceptual quality and introduces artificial colours; making it also difficult for humans to classify images and recognise objects. In this letter, we propose a method to enhance the perceptual quality of these adversarial images. The proposed method is attack type agnostic and could be used in associ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03029","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":""},"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":"1903.03029","created_at":"2026-05-17T23:46:35.818696+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03029v3","created_at":"2026-05-17T23:46:35.818696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03029","created_at":"2026-05-17T23:46:35.818696+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCWQLY6YCEXS","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCWQLY6YCEXS35XP","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCWQLY6Y","created_at":"2026-05-18T12:33:30.264802+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/UCWQLY6YCEXS35XPW5JAQNMQIR","json":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR.json","graph_json":"https://pith.science/api/pith-number/UCWQLY6YCEXS35XPW5JAQNMQIR/graph.json","events_json":"https://pith.science/api/pith-number/UCWQLY6YCEXS35XPW5JAQNMQIR/events.json","paper":"https://pith.science/paper/UCWQLY6Y"},"agent_actions":{"view_html":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR","download_json":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR.json","view_paper":"https://pith.science/paper/UCWQLY6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03029&json=true","fetch_graph":"https://pith.science/api/pith-number/UCWQLY6YCEXS35XPW5JAQNMQIR/graph.json","fetch_events":"https://pith.science/api/pith-number/UCWQLY6YCEXS35XPW5JAQNMQIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR/action/storage_attestation","attest_author":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR/action/author_attestation","sign_citation":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR/action/citation_signature","submit_replication":"https://pith.science/pith/UCWQLY6YCEXS35XPW5JAQNMQIR/action/replication_record"}},"created_at":"2026-05-17T23:46:35.818696+00:00","updated_at":"2026-05-17T23:46:35.818696+00:00"}