{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DKHDEUQO6YB7QFSQIPPAC4G6U4","short_pith_number":"pith:DKHDEUQO","schema_version":"1.0","canonical_sha256":"1a8e32520ef603f8165043de0170dea7006ae90b2166047eb65f8bb5e35ba8ce","source":{"kind":"arxiv","id":"2606.31378","version":1},"attestation_state":"computed","paper":{"title":"MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jichao Xie, Peng Yi, Shumin Huo, Tao Hu, Xinlei Liu, Yuxiang Hu, Zhen Zhang","submitted_at":"2026-06-30T09:08:35Z","abstract_excerpt":"Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model and its output information, transferable adversarial attacks exhibit a notably high stealthiness and detection difficulty, making them a significant focus of defense. In this work, we propose a deep learning defense known as multi-source adversarial perturbations elimination (MAPE) to counter diverse transferable attacks. MAPE comprises the si"},"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":"2606.31378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T09:08:35Z","cross_cats_sorted":[],"title_canon_sha256":"26a28dcc7fb5a04009a9e9d65ce1f67aa08568ebd533724979e26bcd9dd0b49f","abstract_canon_sha256":"4eeb17c11b7b9e410e8ec54ba625c91792a3de56e7b8eae92e7508cd3a90c297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:01.273188Z","signature_b64":"2/2YYjyxemS/CPGLm391/NWl7BPNheLcV4nu6EHjdvAPy2n+F4SQ90Dhjv7Yw9Uugrwd9I7sk1Q5Hr6zx0RxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a8e32520ef603f8165043de0170dea7006ae90b2166047eb65f8bb5e35ba8ce","last_reissued_at":"2026-07-01T01:18:01.272728Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:01.272728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jichao Xie, Peng Yi, Shumin Huo, Tao Hu, Xinlei Liu, Yuxiang Hu, Zhen Zhang","submitted_at":"2026-06-30T09:08:35Z","abstract_excerpt":"Neural networks are vulnerable to meticulously crafted adversarial examples, leading to high-confidence misclassifications in image classification tasks. Due to their consistency with regular input patterns and the absence of reliance on the target model and its output information, transferable adversarial attacks exhibit a notably high stealthiness and detection difficulty, making them a significant focus of defense. In this work, we propose a deep learning defense known as multi-source adversarial perturbations elimination (MAPE) to counter diverse transferable attacks. MAPE comprises the si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31378","kind":"arxiv","version":1},"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/2606.31378/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":"2606.31378","created_at":"2026-07-01T01:18:01.272798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31378v1","created_at":"2026-07-01T01:18:01.272798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31378","created_at":"2026-07-01T01:18:01.272798+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKHDEUQO6YB7","created_at":"2026-07-01T01:18:01.272798+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKHDEUQO6YB7QFSQ","created_at":"2026-07-01T01:18:01.272798+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKHDEUQO","created_at":"2026-07-01T01:18:01.272798+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/DKHDEUQO6YB7QFSQIPPAC4G6U4","json":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4.json","graph_json":"https://pith.science/api/pith-number/DKHDEUQO6YB7QFSQIPPAC4G6U4/graph.json","events_json":"https://pith.science/api/pith-number/DKHDEUQO6YB7QFSQIPPAC4G6U4/events.json","paper":"https://pith.science/paper/DKHDEUQO"},"agent_actions":{"view_html":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4","download_json":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4.json","view_paper":"https://pith.science/paper/DKHDEUQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31378&json=true","fetch_graph":"https://pith.science/api/pith-number/DKHDEUQO6YB7QFSQIPPAC4G6U4/graph.json","fetch_events":"https://pith.science/api/pith-number/DKHDEUQO6YB7QFSQIPPAC4G6U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4/action/storage_attestation","attest_author":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4/action/author_attestation","sign_citation":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4/action/citation_signature","submit_replication":"https://pith.science/pith/DKHDEUQO6YB7QFSQIPPAC4G6U4/action/replication_record"}},"created_at":"2026-07-01T01:18:01.272798+00:00","updated_at":"2026-07-01T01:18:01.272798+00:00"}