{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KRCKV4GD5VVFJFJGQS5U4YO6V7","short_pith_number":"pith:KRCKV4GD","schema_version":"1.0","canonical_sha256":"5444aaf0c3ed6a54952684bb4e61deaff3da3602ca576ae6b72c0333877a67fb","source":{"kind":"arxiv","id":"1712.02051","version":2},"attestation_state":"computed","paper":{"title":"Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cho-Jui Hsieh, Hongge Chen, Huan Zhang, Jinfeng Yi, Pin-Yu Chen","submitted_at":"2017-12-06T06:08:59Z","abstract_excerpt":"Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) for language caption generation. To study the robustness of language grounding to adversarial perturbations in machine vision and perception, we propose Show-and-Fool, a novel algorithm for crafting adversarial examples in neural image captioning. The proposed algorithm provides two evaluation approaches, which check"},"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":"1712.02051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-06T06:08:59Z","cross_cats_sorted":[],"title_canon_sha256":"b8d6c1f14e7f0b5c36e15759bccd015628ded5d24bf1fc155a427b99f504c131","abstract_canon_sha256":"444096ff23e909a727402dce722ec3eabb5b4a9f8fbffe2f136b260a0fba2e5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:30.311139Z","signature_b64":"NpP3EeC1UeFHjrv96a0DBd/sg07urF6D2Yl4Iiy9K2MTTUUoHT0hvbpc18x5SOehlRALGr0Rhr+WUmv6nlxKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5444aaf0c3ed6a54952684bb4e61deaff3da3602ca576ae6b72c0333877a67fb","last_reissued_at":"2026-05-18T00:15:30.310650Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:30.310650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cho-Jui Hsieh, Hongge Chen, Huan Zhang, Jinfeng Yi, Pin-Yu Chen","submitted_at":"2017-12-06T06:08:59Z","abstract_excerpt":"Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) for language caption generation. To study the robustness of language grounding to adversarial perturbations in machine vision and perception, we propose Show-and-Fool, a novel algorithm for crafting adversarial examples in neural image captioning. The proposed algorithm provides two evaluation approaches, which check"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02051","kind":"arxiv","version":2},"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":"1712.02051","created_at":"2026-05-18T00:15:30.310725+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.02051v2","created_at":"2026-05-18T00:15:30.310725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02051","created_at":"2026-05-18T00:15:30.310725+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRCKV4GD5VVF","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRCKV4GD5VVFJFJG","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRCKV4GD","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2406.09250","citing_title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2508.06964","citing_title":"Adversarial Video Promotion Against Text-to-Video Retrieval","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7","json":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7.json","graph_json":"https://pith.science/api/pith-number/KRCKV4GD5VVFJFJGQS5U4YO6V7/graph.json","events_json":"https://pith.science/api/pith-number/KRCKV4GD5VVFJFJGQS5U4YO6V7/events.json","paper":"https://pith.science/paper/KRCKV4GD"},"agent_actions":{"view_html":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7","download_json":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7.json","view_paper":"https://pith.science/paper/KRCKV4GD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.02051&json=true","fetch_graph":"https://pith.science/api/pith-number/KRCKV4GD5VVFJFJGQS5U4YO6V7/graph.json","fetch_events":"https://pith.science/api/pith-number/KRCKV4GD5VVFJFJGQS5U4YO6V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7/action/storage_attestation","attest_author":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7/action/author_attestation","sign_citation":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7/action/citation_signature","submit_replication":"https://pith.science/pith/KRCKV4GD5VVFJFJGQS5U4YO6V7/action/replication_record"}},"created_at":"2026-05-18T00:15:30.310725+00:00","updated_at":"2026-05-18T00:15:30.310725+00:00"}