{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YAQ7RBIZR35XPLPUYJUMDCO2ZG","short_pith_number":"pith:YAQ7RBIZ","schema_version":"1.0","canonical_sha256":"c021f885198efb77adf4c268c189dac9adc69705ff5d5011e463c23fc7391826","source":{"kind":"arxiv","id":"1811.01629","version":1},"attestation_state":"computed","paper":{"title":"On the Transferability of Adversarial Examples Against CNN-Based Image Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Benedetta Tondi, Ehsan Nowroozi, Kassem Kallas, Mauro Barni","submitted_at":"2018-11-05T11:52:47Z","abstract_excerpt":"Recent studies have shown that Convolutional Neural Networks (CNN) are relatively easy to attack through the generation of so-called adversarial examples. Such vulnerability also affects CNN-based image forensic tools. Research in deep learning has shown that adversarial examples exhibit a certain degree of transferability, i.e., they maintain part of their effectiveness even against CNN models other than the one targeted by the attack. This is a very strong property undermining the usability of CNN's in security-oriented applications. In this paper, we investigate if attack transferability al"},"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":"1811.01629","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-11-05T11:52:47Z","cross_cats_sorted":[],"title_canon_sha256":"5364e7463c0322a0da034b5cf27bd94d9eda3ca304bfc58708fdccd2f404394f","abstract_canon_sha256":"58d95912a274836f3693341d9312668201c5036d81f2366bed0bdaf5ccc4f740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:33.721239Z","signature_b64":"KgQX2lBVV+qHyRnuMhYcw0EkXTIcU9YO4qQDSLJZqfYo2Iut2gMYRN33ca1FYen+cyaU6N2N2fUPtdix3ha/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c021f885198efb77adf4c268c189dac9adc69705ff5d5011e463c23fc7391826","last_reissued_at":"2026-05-18T00:01:33.720761Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:33.720761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Transferability of Adversarial Examples Against CNN-Based Image Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Benedetta Tondi, Ehsan Nowroozi, Kassem Kallas, Mauro Barni","submitted_at":"2018-11-05T11:52:47Z","abstract_excerpt":"Recent studies have shown that Convolutional Neural Networks (CNN) are relatively easy to attack through the generation of so-called adversarial examples. Such vulnerability also affects CNN-based image forensic tools. Research in deep learning has shown that adversarial examples exhibit a certain degree of transferability, i.e., they maintain part of their effectiveness even against CNN models other than the one targeted by the attack. This is a very strong property undermining the usability of CNN's in security-oriented applications. In this paper, we investigate if attack transferability al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01629","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":""},"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":"1811.01629","created_at":"2026-05-18T00:01:33.720828+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01629v1","created_at":"2026-05-18T00:01:33.720828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01629","created_at":"2026-05-18T00:01:33.720828+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAQ7RBIZR35X","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAQ7RBIZR35XPLPU","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAQ7RBIZ","created_at":"2026-05-18T12:33:04.347982+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/YAQ7RBIZR35XPLPUYJUMDCO2ZG","json":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG.json","graph_json":"https://pith.science/api/pith-number/YAQ7RBIZR35XPLPUYJUMDCO2ZG/graph.json","events_json":"https://pith.science/api/pith-number/YAQ7RBIZR35XPLPUYJUMDCO2ZG/events.json","paper":"https://pith.science/paper/YAQ7RBIZ"},"agent_actions":{"view_html":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG","download_json":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG.json","view_paper":"https://pith.science/paper/YAQ7RBIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01629&json=true","fetch_graph":"https://pith.science/api/pith-number/YAQ7RBIZR35XPLPUYJUMDCO2ZG/graph.json","fetch_events":"https://pith.science/api/pith-number/YAQ7RBIZR35XPLPUYJUMDCO2ZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG/action/storage_attestation","attest_author":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG/action/author_attestation","sign_citation":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG/action/citation_signature","submit_replication":"https://pith.science/pith/YAQ7RBIZR35XPLPUYJUMDCO2ZG/action/replication_record"}},"created_at":"2026-05-18T00:01:33.720828+00:00","updated_at":"2026-05-18T00:01:33.720828+00:00"}