{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:B5Z4LNDNGEN74LRC6S4XTSVPM5","short_pith_number":"pith:B5Z4LNDN","schema_version":"1.0","canonical_sha256":"0f73c5b46d311bfe2e22f4b979caaf676c8562fd9ee57c22cb113e13f45180fe","source":{"kind":"arxiv","id":"1510.05328","version":5},"attestation_state":"computed","paper":{"title":"Exploring the Space of Adversarial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Eduardo Valle, Pedro Tabacof","submitted_at":"2015-10-19T00:54:37Z","abstract_excerpt":"Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images "},"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":"1510.05328","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2015-10-19T00:54:37Z","cross_cats_sorted":[],"title_canon_sha256":"59506c3bdc89c42553938d7888f2d50f7a8c7fe618e92c04f803af96b57c87c2","abstract_canon_sha256":"845f61daa13ff8ab323aa54e4e4702f95ab9c25c9a396edd0488863e89fbd82c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:00.308541Z","signature_b64":"E2e/lQRcXOqCf+THUDZ3fAHsNWPaAhjjclQaXhYrBy+ZhiZ0hPqX84V/aBqudH3haZs0zZPJv3YOVamN0kXBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f73c5b46d311bfe2e22f4b979caaf676c8562fd9ee57c22cb113e13f45180fe","last_reissued_at":"2026-05-18T01:12:00.308186Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:00.308186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Space of Adversarial Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Eduardo Valle, Pedro Tabacof","submitted_at":"2015-10-19T00:54:37Z","abstract_excerpt":"Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.05328","kind":"arxiv","version":5},"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":"1510.05328","created_at":"2026-05-18T01:12:00.308244+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.05328v5","created_at":"2026-05-18T01:12:00.308244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.05328","created_at":"2026-05-18T01:12:00.308244+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5Z4LNDNGEN7","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5Z4LNDNGEN74LRC","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5Z4LNDN","created_at":"2026-05-18T12:29:14.074870+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/B5Z4LNDNGEN74LRC6S4XTSVPM5","json":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5.json","graph_json":"https://pith.science/api/pith-number/B5Z4LNDNGEN74LRC6S4XTSVPM5/graph.json","events_json":"https://pith.science/api/pith-number/B5Z4LNDNGEN74LRC6S4XTSVPM5/events.json","paper":"https://pith.science/paper/B5Z4LNDN"},"agent_actions":{"view_html":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5","download_json":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5.json","view_paper":"https://pith.science/paper/B5Z4LNDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.05328&json=true","fetch_graph":"https://pith.science/api/pith-number/B5Z4LNDNGEN74LRC6S4XTSVPM5/graph.json","fetch_events":"https://pith.science/api/pith-number/B5Z4LNDNGEN74LRC6S4XTSVPM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5/action/storage_attestation","attest_author":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5/action/author_attestation","sign_citation":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5/action/citation_signature","submit_replication":"https://pith.science/pith/B5Z4LNDNGEN74LRC6S4XTSVPM5/action/replication_record"}},"created_at":"2026-05-18T01:12:00.308244+00:00","updated_at":"2026-05-18T01:12:00.308244+00:00"}