{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:STVH56VDDKAWDEF3DSCC3PZYIN","short_pith_number":"pith:STVH56VD","schema_version":"1.0","canonical_sha256":"94ea7efaa31a816190bb1c842dbf384341b54a24603c68ea6aabde3dc5aa9ed4","source":{"kind":"arxiv","id":"2210.13463","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Future","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Guo-jun Qi, Mubarak Shah","submitted_at":"2022-10-23T13:14:06Z","abstract_excerpt":"In this paper, we review adversarial pretraining of self-supervised deep networks including both convolutional neural networks and vision transformers. Unlike the adversarial training with access to labeled examples, adversarial pretraining is complicated as it only has access to unlabeled examples. To incorporate adversaries into pretraining models on either input or feature level, we find that existing approaches are largely categorized into two groups: memory-free instance-wise attacks imposing worst-case perturbations on individual examples, and memory-based adversaries shared across examp"},"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":"2210.13463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-23T13:14:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ffcf01067d3ac0833066f4f2ac564d1c9a7562616ac91b60e52859ee5aa191ff","abstract_canon_sha256":"782a4d9f766d7dbf9b284a63b98acbb6a0ccdbf8579a5b93b96f0999a347c65f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:18.691033Z","signature_b64":"whrVcyUIe53kbRL/U5Rk8GeAe6IIjKaUKmw5Z04U/JoHZK3RWemmZ2I804MVRn3WLD+ZO7ClPaVS1rMXN6iPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ea7efaa31a816190bb1c842dbf384341b54a24603c68ea6aabde3dc5aa9ed4","last_reissued_at":"2026-07-05T05:10:18.690601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:18.690601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Future","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Guo-jun Qi, Mubarak Shah","submitted_at":"2022-10-23T13:14:06Z","abstract_excerpt":"In this paper, we review adversarial pretraining of self-supervised deep networks including both convolutional neural networks and vision transformers. Unlike the adversarial training with access to labeled examples, adversarial pretraining is complicated as it only has access to unlabeled examples. To incorporate adversaries into pretraining models on either input or feature level, we find that existing approaches are largely categorized into two groups: memory-free instance-wise attacks imposing worst-case perturbations on individual examples, and memory-based adversaries shared across examp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13463","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/2210.13463/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":"2210.13463","created_at":"2026-07-05T05:10:18.690664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13463v1","created_at":"2026-07-05T05:10:18.690664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13463","created_at":"2026-07-05T05:10:18.690664+00:00"},{"alias_kind":"pith_short_12","alias_value":"STVH56VDDKAW","created_at":"2026-07-05T05:10:18.690664+00:00"},{"alias_kind":"pith_short_16","alias_value":"STVH56VDDKAWDEF3","created_at":"2026-07-05T05:10:18.690664+00:00"},{"alias_kind":"pith_short_8","alias_value":"STVH56VD","created_at":"2026-07-05T05:10:18.690664+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/STVH56VDDKAWDEF3DSCC3PZYIN","json":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN.json","graph_json":"https://pith.science/api/pith-number/STVH56VDDKAWDEF3DSCC3PZYIN/graph.json","events_json":"https://pith.science/api/pith-number/STVH56VDDKAWDEF3DSCC3PZYIN/events.json","paper":"https://pith.science/paper/STVH56VD"},"agent_actions":{"view_html":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN","download_json":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN.json","view_paper":"https://pith.science/paper/STVH56VD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13463&json=true","fetch_graph":"https://pith.science/api/pith-number/STVH56VDDKAWDEF3DSCC3PZYIN/graph.json","fetch_events":"https://pith.science/api/pith-number/STVH56VDDKAWDEF3DSCC3PZYIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN/action/storage_attestation","attest_author":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN/action/author_attestation","sign_citation":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN/action/citation_signature","submit_replication":"https://pith.science/pith/STVH56VDDKAWDEF3DSCC3PZYIN/action/replication_record"}},"created_at":"2026-07-05T05:10:18.690664+00:00","updated_at":"2026-07-05T05:10:18.690664+00:00"}