{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PX6P24VYB3EW4YWCKYLUROP62B","short_pith_number":"pith:PX6P24VY","schema_version":"1.0","canonical_sha256":"7dfcfd72b80ec96e62c2561748b9fed07001e36847d23e1d25549e1ce16dcd39","source":{"kind":"arxiv","id":"2606.26207","version":1},"attestation_state":"computed","paper":{"title":"The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Benedetta Tondi, Giovanni Bellettini, Mauro Barni, Nasrin Malekzadeh Goradel, Niccolo Pancino, Yaser Gholizade Atani","submitted_at":"2026-06-24T16:59:39Z","abstract_excerpt":"Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this work, we present a systematic study of the role of input dimensionality in both the emergence and the targeted control of adversarial examples. We first analyse the scope and limitations of existing theoretical frameworks based on concentration of measure, showing that real image classes exhibit strong empirical local"},"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":"2606.26207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T16:59:39Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"3915caa39cc6c3a29b18b00c94df9562b3a61dfea65b6c558ba2544c47530562","abstract_canon_sha256":"7a9527594b1d130b24f01e806ba1ae4987037163356457a1221f4149a18f30f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:29.479641Z","signature_b64":"Qh4zFxo0yH6wkqHWDi2qMkLcMf37cJkiaZkspNi94dxdmrh4VmnGjlnBiVfAFU5WYhv04KwiOSFjF31D3ZcbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dfcfd72b80ec96e62c2561748b9fed07001e36847d23e1d25549e1ce16dcd39","last_reissued_at":"2026-06-26T00:15:29.479099Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:29.479099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"stat.ML","authors_text":"Benedetta Tondi, Giovanni Bellettini, Mauro Barni, Nasrin Malekzadeh Goradel, Niccolo Pancino, Yaser Gholizade Atani","submitted_at":"2026-06-24T16:59:39Z","abstract_excerpt":"Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this work, we present a systematic study of the role of input dimensionality in both the emergence and the targeted control of adversarial examples. We first analyse the scope and limitations of existing theoretical frameworks based on concentration of measure, showing that real image classes exhibit strong empirical local"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26207","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/2606.26207/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":"2606.26207","created_at":"2026-06-26T00:15:29.479161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26207v1","created_at":"2026-06-26T00:15:29.479161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26207","created_at":"2026-06-26T00:15:29.479161+00:00"},{"alias_kind":"pith_short_12","alias_value":"PX6P24VYB3EW","created_at":"2026-06-26T00:15:29.479161+00:00"},{"alias_kind":"pith_short_16","alias_value":"PX6P24VYB3EW4YWC","created_at":"2026-06-26T00:15:29.479161+00:00"},{"alias_kind":"pith_short_8","alias_value":"PX6P24VY","created_at":"2026-06-26T00:15:29.479161+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/PX6P24VYB3EW4YWCKYLUROP62B","json":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B.json","graph_json":"https://pith.science/api/pith-number/PX6P24VYB3EW4YWCKYLUROP62B/graph.json","events_json":"https://pith.science/api/pith-number/PX6P24VYB3EW4YWCKYLUROP62B/events.json","paper":"https://pith.science/paper/PX6P24VY"},"agent_actions":{"view_html":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B","download_json":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B.json","view_paper":"https://pith.science/paper/PX6P24VY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26207&json=true","fetch_graph":"https://pith.science/api/pith-number/PX6P24VYB3EW4YWCKYLUROP62B/graph.json","fetch_events":"https://pith.science/api/pith-number/PX6P24VYB3EW4YWCKYLUROP62B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B/action/storage_attestation","attest_author":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B/action/author_attestation","sign_citation":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B/action/citation_signature","submit_replication":"https://pith.science/pith/PX6P24VYB3EW4YWCKYLUROP62B/action/replication_record"}},"created_at":"2026-06-26T00:15:29.479161+00:00","updated_at":"2026-06-26T00:15:29.479161+00:00"}