{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RMMGUOW6B2RDHVCMREU7OGCFLK","short_pith_number":"pith:RMMGUOW6","canonical_record":{"source":{"id":"2411.02391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"145061438d4647ad1b3bb84d2286dfa07cdcf5b1b7e8b266a8d9a02231aa0a0c","abstract_canon_sha256":"6ff6b31274ad8a05b6515828015d1d515c6a27d7c2278e27f62690a0c68d684c"},"schema_version":"1.0"},"canonical_sha256":"8b186a3ade0ea233d44c8929f718455aa3f6182dc3236064211fbfba2f2f006b","source":{"kind":"arxiv","id":"2411.02391","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02391","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02391v2","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02391","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"RMMGUOW6B2RD","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"RMMGUOW6B2RDHVCM","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"RMMGUOW6","created_at":"2026-07-05T11:09:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RMMGUOW6B2RDHVCMREU7OGCFLK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"145061438d4647ad1b3bb84d2286dfa07cdcf5b1b7e8b266a8d9a02231aa0a0c","abstract_canon_sha256":"6ff6b31274ad8a05b6515828015d1d515c6a27d7c2278e27f62690a0c68d684c"},"schema_version":"1.0"},"canonical_sha256":"8b186a3ade0ea233d44c8929f718455aa3f6182dc3236064211fbfba2f2f006b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:03.707625Z","signature_b64":"N8ShcaEJHwTUIbbRIUs9cdduz9nHO2MucKBtd5hwdJmq5YwudONMtf6nfX5dJOpgHk6SXKn9bnDVrLi05MSABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b186a3ade0ea233d44c8929f718455aa3f6182dc3236064211fbfba2f2f006b","last_reissued_at":"2026-07-05T11:09:03.707172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:03.707172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02391","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVVRmeZcAjamd6LYczoVWmDbzztXM9mi1zKgcU1zkYiBzIOOgTjvTaJxp/hZb1q7ybp4VutKA39Kw4/MGI0EBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T09:51:26.188773Z"},"content_sha256":"07cf5739a5b87b24a37f59ced4f84c2681ded3bfb51322e2869fca75d2690699","schema_version":"1.0","event_id":"sha256:07cf5739a5b87b24a37f59ced4f84c2681ded3bfb51322e2869fca75d2690699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RMMGUOW6B2RDHVCMREU7OGCFLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attacking Vision-Language Computer Agents via Pop-ups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Tao Yu, Yanzhe Zhang","submitted_at":"2024-11-04T18:56:42Z","abstract_excerpt":"Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02391","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.02391/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":"2026-07-05T11:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRitJrJTiQnztOzsWLW5+quPosDs4BPfUh536soL3HZVY2zI873C92jSXKZgFI2xRKESjyYkQWywnOni+12QBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T09:51:26.189129Z"},"content_sha256":"b107f2f77a17bd657146033cdbeb531f0a8000f07ca7b1684c434303924aaaed","schema_version":"1.0","event_id":"sha256:b107f2f77a17bd657146033cdbeb531f0a8000f07ca7b1684c434303924aaaed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/bundle.json","state_url":"https://pith.science/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/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":"2026-07-27T09:51:26Z","links":{"resolver":"https://pith.science/pith/RMMGUOW6B2RDHVCMREU7OGCFLK","bundle":"https://pith.science/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/bundle.json","state":"https://pith.science/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMMGUOW6B2RDHVCMREU7OGCFLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RMMGUOW6B2RDHVCMREU7OGCFLK","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":"6ff6b31274ad8a05b6515828015d1d515c6a27d7c2278e27f62690a0c68d684c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:56:42Z","title_canon_sha256":"145061438d4647ad1b3bb84d2286dfa07cdcf5b1b7e8b266a8d9a02231aa0a0c"},"schema_version":"1.0","source":{"id":"2411.02391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02391","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02391v2","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02391","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"RMMGUOW6B2RD","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"RMMGUOW6B2RDHVCM","created_at":"2026-07-05T11:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"RMMGUOW6","created_at":"2026-07-05T11:09:03Z"}],"graph_snapshots":[{"event_id":"sha256:b107f2f77a17bd657146033cdbeb531f0a8000f07ca7b1684c434303924aaaed","target":"graph","created_at":"2026-07-05T11:09:03Z","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/2411.02391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents powered by large vision and language models (VLM) have demonstrated significant potential in completing daily computer tasks, such as browsing the web to book travel and operating desktop software, which requires agents to understand these interfaces. Despite such visual inputs becoming more integrated into agentic applications, what types of risks and attacks exist around them still remain unclear. In this work, we demonstrate that VLM agents can be easily attacked by a set of carefully designed adversarial pop-ups, which human users would typically recognize and ignore. Thi","authors_text":"Diyi Yang, Tao Yu, Yanzhe Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:56:42Z","title":"Attacking Vision-Language Computer Agents via Pop-ups"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02391","kind":"arxiv","version":2},"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":"sha256:07cf5739a5b87b24a37f59ced4f84c2681ded3bfb51322e2869fca75d2690699","target":"record","created_at":"2026-07-05T11:09:03Z","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":"6ff6b31274ad8a05b6515828015d1d515c6a27d7c2278e27f62690a0c68d684c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T18:56:42Z","title_canon_sha256":"145061438d4647ad1b3bb84d2286dfa07cdcf5b1b7e8b266a8d9a02231aa0a0c"},"schema_version":"1.0","source":{"id":"2411.02391","kind":"arxiv","version":2}},"canonical_sha256":"8b186a3ade0ea233d44c8929f718455aa3f6182dc3236064211fbfba2f2f006b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b186a3ade0ea233d44c8929f718455aa3f6182dc3236064211fbfba2f2f006b","first_computed_at":"2026-07-05T11:09:03.707172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:03.707172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N8ShcaEJHwTUIbbRIUs9cdduz9nHO2MucKBtd5hwdJmq5YwudONMtf6nfX5dJOpgHk6SXKn9bnDVrLi05MSABA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:03.707625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07cf5739a5b87b24a37f59ced4f84c2681ded3bfb51322e2869fca75d2690699","sha256:b107f2f77a17bd657146033cdbeb531f0a8000f07ca7b1684c434303924aaaed"],"state_sha256":"94cbf33121327bf9a35bd7bae67c1d12ef72f9d624641086e2fc8f9f1be3ee12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/7V42wtOPbaqkU7e/9kWf3HABqLa9lUmxTIfIvcGwrvlEgBg6kQjyJ1r8qMfLq/mJly6j0yP33wOzVmVuOIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T09:51:26.191482Z","bundle_sha256":"a4a119d191ad6ee1e9d100834b38aa2e23775b74d3c8f711177bf1f0d5e5c6e3"}}