{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SLSL65ORV357SHQXLSN7PDRAHK","short_pith_number":"pith:SLSL65OR","schema_version":"1.0","canonical_sha256":"92e4bf75d1aefbf91e175c9bf78e203ab917c71cbc6c5330b1d292391131692e","source":{"kind":"arxiv","id":"2206.07406","version":1},"attestation_state":"computed","paper":{"title":"Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jonah O'Brien Weiss, Sandip Kundu, Tiago Alves","submitted_at":"2022-06-15T09:13:35Z","abstract_excerpt":"The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization. These techniques accelerate model inference, reduce power consumption, and reduce the size and complexity of the hardware necessary to run DNNs, all with little to no loss in accuracy. However, since DNNs are vulnerable to adversarial inputs, it is important to consider the relationship between compression and adversarial robustness. In this work, we investigate the adversarial robustness of models produced by several irregular pruni"},"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":"2206.07406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T09:13:35Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"cbd8a5d32b1f21c9cab8bea5dac6d792ce231ff9ff7cbf4c7683226d994a3c1e","abstract_canon_sha256":"e8d89eb58ed200ae06f5608fbaf810a151cce4888ce4cb6fe9ecff6c774ef50c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:04.329032Z","signature_b64":"aYAr0xhXkCyDxAVS+Qvmc0AeHlLTs+p1widg5c/cnfAFbcN4JCbLxvh6jLmFEr0lbIqXrQlF/xCn/k92h8CpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e4bf75d1aefbf91e175c9bf78e203ab917c71cbc6c5330b1d292391131692e","last_reissued_at":"2026-07-05T04:32:04.328632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:04.328632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jonah O'Brien Weiss, Sandip Kundu, Tiago Alves","submitted_at":"2022-06-15T09:13:35Z","abstract_excerpt":"The prevalence and success of Deep Neural Network (DNN) applications in recent years have motivated research on DNN compression, such as pruning and quantization. These techniques accelerate model inference, reduce power consumption, and reduce the size and complexity of the hardware necessary to run DNNs, all with little to no loss in accuracy. However, since DNNs are vulnerable to adversarial inputs, it is important to consider the relationship between compression and adversarial robustness. In this work, we investigate the adversarial robustness of models produced by several irregular pruni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07406","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/2206.07406/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":"2206.07406","created_at":"2026-07-05T04:32:04.328685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07406v1","created_at":"2026-07-05T04:32:04.328685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07406","created_at":"2026-07-05T04:32:04.328685+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLSL65ORV357","created_at":"2026-07-05T04:32:04.328685+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLSL65ORV357SHQX","created_at":"2026-07-05T04:32:04.328685+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLSL65OR","created_at":"2026-07-05T04:32:04.328685+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/SLSL65ORV357SHQXLSN7PDRAHK","json":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK.json","graph_json":"https://pith.science/api/pith-number/SLSL65ORV357SHQXLSN7PDRAHK/graph.json","events_json":"https://pith.science/api/pith-number/SLSL65ORV357SHQXLSN7PDRAHK/events.json","paper":"https://pith.science/paper/SLSL65OR"},"agent_actions":{"view_html":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK","download_json":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK.json","view_paper":"https://pith.science/paper/SLSL65OR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07406&json=true","fetch_graph":"https://pith.science/api/pith-number/SLSL65ORV357SHQXLSN7PDRAHK/graph.json","fetch_events":"https://pith.science/api/pith-number/SLSL65ORV357SHQXLSN7PDRAHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK/action/storage_attestation","attest_author":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK/action/author_attestation","sign_citation":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK/action/citation_signature","submit_replication":"https://pith.science/pith/SLSL65ORV357SHQXLSN7PDRAHK/action/replication_record"}},"created_at":"2026-07-05T04:32:04.328685+00:00","updated_at":"2026-07-05T04:32:04.328685+00:00"}