{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PVD6PZFU3R7OJJRMGPFL3ETTFB","short_pith_number":"pith:PVD6PZFU","schema_version":"1.0","canonical_sha256":"7d47e7e4b4dc7ee4a62c33cabd9273287b079f343beacacd24d8b7fb3afc5721","source":{"kind":"arxiv","id":"2106.14815","version":3},"attestation_state":"computed","paper":{"title":"Feature Importance Guided Attack: A Model Agnostic Adversarial Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Anjali S., Archana Sreekumar, Gilad Gressel, Kalyani Harikumar, Krishnashree Achuthan, Niranjan Hegde, Rishikumar Radhakrishnan","submitted_at":"2021-06-28T15:46:22Z","abstract_excerpt":"Research in adversarial learning has primarily focused on homogeneous unstructured datasets, which often map into the problem space naturally. Inverting a feature space attack on heterogeneous datasets into the problem space is much more challenging, particularly the task of finding the perturbation to perform. This work presents a formal search strategy: the `Feature Importance Guided Attack' (FIGA), which finds perturbations in the feature space of heterogeneous tabular datasets to produce evasion attacks. We first demonstrate FIGA in the feature space and then in the problem space. FIGA ass"},"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":"2106.14815","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-28T15:46:22Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"e42b691f8f4c070a877652aa89cbd23d11821dcf881dca74c99583cc6f0a7ece","abstract_canon_sha256":"acffd53939f31baf75c04fa294f0a353b2d0a405400cfa48c71c1f52010f5017"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:42.692472Z","signature_b64":"8aAZWXiPKbjIMSbygpfGX9cebbwOMd05WI5VUinrWFwztfXmh/dgXZGu8z02Cp5d6/WQePYL+6YHNbOlKGuLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d47e7e4b4dc7ee4a62c33cabd9273287b079f343beacacd24d8b7fb3afc5721","last_reissued_at":"2026-07-05T05:32:42.692046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:42.692046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Importance Guided Attack: A Model Agnostic Adversarial Attack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Anjali S., Archana Sreekumar, Gilad Gressel, Kalyani Harikumar, Krishnashree Achuthan, Niranjan Hegde, Rishikumar Radhakrishnan","submitted_at":"2021-06-28T15:46:22Z","abstract_excerpt":"Research in adversarial learning has primarily focused on homogeneous unstructured datasets, which often map into the problem space naturally. Inverting a feature space attack on heterogeneous datasets into the problem space is much more challenging, particularly the task of finding the perturbation to perform. This work presents a formal search strategy: the `Feature Importance Guided Attack' (FIGA), which finds perturbations in the feature space of heterogeneous tabular datasets to produce evasion attacks. We first demonstrate FIGA in the feature space and then in the problem space. FIGA ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14815","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.14815/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":"2106.14815","created_at":"2026-07-05T05:32:42.692114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14815v3","created_at":"2026-07-05T05:32:42.692114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14815","created_at":"2026-07-05T05:32:42.692114+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVD6PZFU3R7O","created_at":"2026-07-05T05:32:42.692114+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVD6PZFU3R7OJJRM","created_at":"2026-07-05T05:32:42.692114+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVD6PZFU","created_at":"2026-07-05T05:32:42.692114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00777","citing_title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB","json":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB.json","graph_json":"https://pith.science/api/pith-number/PVD6PZFU3R7OJJRMGPFL3ETTFB/graph.json","events_json":"https://pith.science/api/pith-number/PVD6PZFU3R7OJJRMGPFL3ETTFB/events.json","paper":"https://pith.science/paper/PVD6PZFU"},"agent_actions":{"view_html":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB","download_json":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB.json","view_paper":"https://pith.science/paper/PVD6PZFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14815&json=true","fetch_graph":"https://pith.science/api/pith-number/PVD6PZFU3R7OJJRMGPFL3ETTFB/graph.json","fetch_events":"https://pith.science/api/pith-number/PVD6PZFU3R7OJJRMGPFL3ETTFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB/action/storage_attestation","attest_author":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB/action/author_attestation","sign_citation":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB/action/citation_signature","submit_replication":"https://pith.science/pith/PVD6PZFU3R7OJJRMGPFL3ETTFB/action/replication_record"}},"created_at":"2026-07-05T05:32:42.692114+00:00","updated_at":"2026-07-05T05:32:42.692114+00:00"}