{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CAXPHNVXTA6P27EKMHHICC7MCP","short_pith_number":"pith:CAXPHNVX","schema_version":"1.0","canonical_sha256":"102ef3b6b7983cfd7c8a61ce810bec13e6204729f5f64e3d8703472be33d926e","source":{"kind":"arxiv","id":"1711.01991","version":3},"attestation_state":"computed","paper":{"title":"Mitigating Adversarial Effects Through Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren","submitted_at":"2017-11-06T16:22:54Z","abstract_excerpt":"Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause convolutional neural networks to fail. In this paper, we propose to utilize randomization at inference time to mitigate adversarial effects. Specifically, we use two randomization operations: random resizing, which resizes the input images to a random size, and random padding, which pads zeros around the input images in a random manner. Extensive experiments demons"},"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":"1711.01991","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-06T16:22:54Z","cross_cats_sorted":[],"title_canon_sha256":"8ac3e54d34d6effe465416c36a91f452656fc934604fcbf90be1652c346d1542","abstract_canon_sha256":"30912c7c5b527ac3f953d24186326f361db90fc954924fa35d7196e8fb7604c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:15.888899Z","signature_b64":"W84Fw5K96TJNPBUUJ6DOiBMNRS0W86Rh+WkqLUa/ngEx2Ib32xw5YtQLqpRxAHc/CG6cq+i0zj93OLv5xk4ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"102ef3b6b7983cfd7c8a61ce810bec13e6204729f5f64e3d8703472be33d926e","last_reissued_at":"2026-05-18T00:22:15.888220Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:15.888220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Adversarial Effects Through Randomization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren","submitted_at":"2017-11-06T16:22:54Z","abstract_excerpt":"Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause convolutional neural networks to fail. In this paper, we propose to utilize randomization at inference time to mitigate adversarial effects. Specifically, we use two randomization operations: random resizing, which resizes the input images to a random size, and random padding, which pads zeros around the input images in a random manner. Extensive experiments demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01991","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":""},"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":"1711.01991","created_at":"2026-05-18T00:22:15.888331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01991v3","created_at":"2026-05-18T00:22:15.888331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01991","created_at":"2026-05-18T00:22:15.888331+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAXPHNVXTA6P","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAXPHNVXTA6P27EK","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAXPHNVX","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":245,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP","json":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP.json","graph_json":"https://pith.science/api/pith-number/CAXPHNVXTA6P27EKMHHICC7MCP/graph.json","events_json":"https://pith.science/api/pith-number/CAXPHNVXTA6P27EKMHHICC7MCP/events.json","paper":"https://pith.science/paper/CAXPHNVX"},"agent_actions":{"view_html":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP","download_json":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP.json","view_paper":"https://pith.science/paper/CAXPHNVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01991&json=true","fetch_graph":"https://pith.science/api/pith-number/CAXPHNVXTA6P27EKMHHICC7MCP/graph.json","fetch_events":"https://pith.science/api/pith-number/CAXPHNVXTA6P27EKMHHICC7MCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP/action/storage_attestation","attest_author":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP/action/author_attestation","sign_citation":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP/action/citation_signature","submit_replication":"https://pith.science/pith/CAXPHNVXTA6P27EKMHHICC7MCP/action/replication_record"}},"created_at":"2026-05-18T00:22:15.888331+00:00","updated_at":"2026-05-18T00:22:15.888331+00:00"}