{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZRHDR4TSDF6OZHJCNHFGVP6FZ","short_pith_number":"pith:FZRHDR4T","schema_version":"1.0","canonical_sha256":"2e6271c79390cbe764e9134e5355fe2e7f42f10c0243d54e54f3d227f75086dd","source":{"kind":"arxiv","id":"2504.13209","version":1},"attestation_state":"computed","paper":{"title":"On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chenghang Ye, Cui Tang, Jun Zhang, Kailong Wang, Liting Zhou, Tianlong Yu, Ting Bi, Yang Yang, Zheyu Yang, Ziyi Zhou, Zui Tao","submitted_at":"2025-04-16T05:18:36Z","abstract_excerpt":"Augmented Reality (AR) and Multimodal Large Language Models (LLMs) are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility of orchestrating AR-driven Social Engineering attacks using Multimodal LLM for the first time, via our proposed SEAR framework, which operates through three key phases: (1) AR-based social context synthesis, which fuses Multimodal inputs (visual, auditory and environmental cues); (2) role-based Mu"},"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":"2504.13209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2025-04-16T05:18:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24070e40927762b30352cd3227f088155cc751d2cee3608474f8d75c95f5121e","abstract_canon_sha256":"c1a56465b4ee2d6961d924ad73c994b0d01b0c1c953b4f0960f1682dce31836a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:50.504459Z","signature_b64":"eiTc6xLXlyibl0XyyOaQZRaFmzrsWdhF5lIB16n6qI/CR92aVc1wiyEhVtLZACW5JRLPf4wW3qxCoGTywQHsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e6271c79390cbe764e9134e5355fe2e7f42f10c0243d54e54f3d227f75086dd","last_reissued_at":"2026-07-05T10:50:50.503870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:50.503870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chenghang Ye, Cui Tang, Jun Zhang, Kailong Wang, Liting Zhou, Tianlong Yu, Ting Bi, Yang Yang, Zheyu Yang, Ziyi Zhou, Zui Tao","submitted_at":"2025-04-16T05:18:36Z","abstract_excerpt":"Augmented Reality (AR) and Multimodal Large Language Models (LLMs) are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility of orchestrating AR-driven Social Engineering attacks using Multimodal LLM for the first time, via our proposed SEAR framework, which operates through three key phases: (1) AR-based social context synthesis, which fuses Multimodal inputs (visual, auditory and environmental cues); (2) role-based Mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13209","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/2504.13209/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.13209","created_at":"2026-07-05T10:50:50.503948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13209v1","created_at":"2026-07-05T10:50:50.503948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13209","created_at":"2026-07-05T10:50:50.503948+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZRHDR4TSDF6","created_at":"2026-07-05T10:50:50.503948+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZRHDR4TSDF6OZHJ","created_at":"2026-07-05T10:50:50.503948+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZRHDR4T","created_at":"2026-07-05T10:50:50.503948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.21457","citing_title":"SoK: Exposing the Generation and Detection Gaps in LLM-Generated Phishing","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ","json":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ.json","graph_json":"https://pith.science/api/pith-number/FZRHDR4TSDF6OZHJCNHFGVP6FZ/graph.json","events_json":"https://pith.science/api/pith-number/FZRHDR4TSDF6OZHJCNHFGVP6FZ/events.json","paper":"https://pith.science/paper/FZRHDR4T"},"agent_actions":{"view_html":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ","download_json":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ.json","view_paper":"https://pith.science/paper/FZRHDR4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13209&json=true","fetch_graph":"https://pith.science/api/pith-number/FZRHDR4TSDF6OZHJCNHFGVP6FZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FZRHDR4TSDF6OZHJCNHFGVP6FZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ/action/storage_attestation","attest_author":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ/action/author_attestation","sign_citation":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ/action/citation_signature","submit_replication":"https://pith.science/pith/FZRHDR4TSDF6OZHJCNHFGVP6FZ/action/replication_record"}},"created_at":"2026-07-05T10:50:50.503948+00:00","updated_at":"2026-07-05T10:50:50.503948+00:00"}