{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G3W3JAXOPINZY6M7UTZTZ7W7SC","short_pith_number":"pith:G3W3JAXO","canonical_record":{"source":{"id":"2107.03050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T07:22:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e907f176027646ebf461137f00a4c03980ee4995352ad58e9df776b02ce94fa","abstract_canon_sha256":"814e0ac33b408b4e5d39bd9c89f58e07ac0539df54bb28a6bce0de531e1261d9"},"schema_version":"1.0"},"canonical_sha256":"36edb482ee7a1b9c799fa4f33cfedf90b1c13a9b6f3c145eab1c28db02ccdfb1","source":{"kind":"arxiv","id":"2107.03050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03050","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03050v1","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03050","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"G3W3JAXOPINZ","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"G3W3JAXOPINZY6M7","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"G3W3JAXO","created_at":"2026-07-05T02:55:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G3W3JAXOPINZY6M7UTZTZ7W7SC","target":"record","payload":{"canonical_record":{"source":{"id":"2107.03050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T07:22:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e907f176027646ebf461137f00a4c03980ee4995352ad58e9df776b02ce94fa","abstract_canon_sha256":"814e0ac33b408b4e5d39bd9c89f58e07ac0539df54bb28a6bce0de531e1261d9"},"schema_version":"1.0"},"canonical_sha256":"36edb482ee7a1b9c799fa4f33cfedf90b1c13a9b6f3c145eab1c28db02ccdfb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:59.504036Z","signature_b64":"h1MHR4H4PsKigv+KXoZdcKKQYnmLEMY6YK9mPN5cmwrIEIjTKYq3odBRxnpn+Zrc4J6nfAUze4vv8joZbMC3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36edb482ee7a1b9c799fa4f33cfedf90b1c13a9b6f3c145eab1c28db02ccdfb1","last_reissued_at":"2026-07-05T02:55:59.503612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:59.503612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.03050","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAZ8lBg0gMXoI7qwSs2GokmA7ztoDqeu9A7MrFaCHggR7cBCUhWVTYR1R516n2D0AFhTRAIHmbkLHCR3MVvyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:41:45.245742Z"},"content_sha256":"b9e3c931b16c7098e098e5ec7498779789525a12b6f769df5c493e5cc381b3ea","schema_version":"1.0","event_id":"sha256:b9e3c931b16c7098e098e5ec7498779789525a12b6f769df5c493e5cc381b3ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G3W3JAXOPINZY6M7UTZTZ7W7SC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controlled Caption Generation for Images Through Adversarial Attacks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ajmal Mian, Mubarak Shah, Naveed Akhtar, Nayyer Aafaq, Wei Liu","submitted_at":"2021-07-07T07:22:41Z","abstract_excerpt":"Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial examples for vision and language models, which typically adopt an encoder-decoder framework consisting of two major components: a Convolutional Neural Network (i.e., CNN) for image feature extraction and a Recurrent Neural Network (RNN) for caption generation. In particular, we investigate attacks on the visual encoder's hidden layer that is fed to the subsequent recurrent network. The existing methods either attack the cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03050","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/2107.03050/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTJFLqi4tB5sTYsI/ooARM7cmUfw5ZPEngEl9ymD6cdxL4LSu/8cNwE4vNqKUM8jZLJJnu6i7QZjpT4Pd9qgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:41:45.246180Z"},"content_sha256":"39b0489f99d3f93ae9009edf6ab8c6bdaec87d7fa2c8c7e268fb29650eeabf14","schema_version":"1.0","event_id":"sha256:39b0489f99d3f93ae9009edf6ab8c6bdaec87d7fa2c8c7e268fb29650eeabf14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/bundle.json","state_url":"https://pith.science/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T18:41:45Z","links":{"resolver":"https://pith.science/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC","bundle":"https://pith.science/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/bundle.json","state":"https://pith.science/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3W3JAXOPINZY6M7UTZTZ7W7SC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G3W3JAXOPINZY6M7UTZTZ7W7SC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"814e0ac33b408b4e5d39bd9c89f58e07ac0539df54bb28a6bce0de531e1261d9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T07:22:41Z","title_canon_sha256":"0e907f176027646ebf461137f00a4c03980ee4995352ad58e9df776b02ce94fa"},"schema_version":"1.0","source":{"id":"2107.03050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03050","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03050v1","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03050","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"G3W3JAXOPINZ","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"G3W3JAXOPINZY6M7","created_at":"2026-07-05T02:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"G3W3JAXO","created_at":"2026-07-05T02:55:59Z"}],"graph_snapshots":[{"event_id":"sha256:39b0489f99d3f93ae9009edf6ab8c6bdaec87d7fa2c8c7e268fb29650eeabf14","target":"graph","created_at":"2026-07-05T02:55:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.03050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning is found to be vulnerable to adversarial examples. However, its adversarial susceptibility in image caption generation is under-explored. We study adversarial examples for vision and language models, which typically adopt an encoder-decoder framework consisting of two major components: a Convolutional Neural Network (i.e., CNN) for image feature extraction and a Recurrent Neural Network (RNN) for caption generation. In particular, we investigate attacks on the visual encoder's hidden layer that is fed to the subsequent recurrent network. The existing methods either attack the cla","authors_text":"Ajmal Mian, Mubarak Shah, Naveed Akhtar, Nayyer Aafaq, Wei Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T07:22:41Z","title":"Controlled Caption Generation for Images Through Adversarial Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03050","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b9e3c931b16c7098e098e5ec7498779789525a12b6f769df5c493e5cc381b3ea","target":"record","created_at":"2026-07-05T02:55:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"814e0ac33b408b4e5d39bd9c89f58e07ac0539df54bb28a6bce0de531e1261d9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T07:22:41Z","title_canon_sha256":"0e907f176027646ebf461137f00a4c03980ee4995352ad58e9df776b02ce94fa"},"schema_version":"1.0","source":{"id":"2107.03050","kind":"arxiv","version":1}},"canonical_sha256":"36edb482ee7a1b9c799fa4f33cfedf90b1c13a9b6f3c145eab1c28db02ccdfb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36edb482ee7a1b9c799fa4f33cfedf90b1c13a9b6f3c145eab1c28db02ccdfb1","first_computed_at":"2026-07-05T02:55:59.503612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:59.503612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h1MHR4H4PsKigv+KXoZdcKKQYnmLEMY6YK9mPN5cmwrIEIjTKYq3odBRxnpn+Zrc4J6nfAUze4vv8joZbMC3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:59.504036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.03050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9e3c931b16c7098e098e5ec7498779789525a12b6f769df5c493e5cc381b3ea","sha256:39b0489f99d3f93ae9009edf6ab8c6bdaec87d7fa2c8c7e268fb29650eeabf14"],"state_sha256":"530ca0a455afca866664c58b0d5f1b357319d9daf763ac1ffb0160acd53f2db0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pnq9LzQvQMCHwkb4K33KfoeC74rotMneARtyQf/QdS81HNRlNVGtG1k5VRCSr/A8/HnrAdQBhbmH68CqipG1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:41:45.248165Z","bundle_sha256":"470832eff100f8377381b1a7bd34990d420a37107ec0c987c4f0e41e516b773f"}}