{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ARDSGIDQBNGBYICXIYJFZNJ6RA","short_pith_number":"pith:ARDSGIDQ","schema_version":"1.0","canonical_sha256":"04472320700b4c1c205746125cb53e882fad506ac60b62ca846bbfff0309be55","source":{"kind":"arxiv","id":"2607.02819","version":1},"attestation_state":"computed","paper":{"title":"Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CR","authors_text":"Jiahao Xu, Olivera Kotevska, Rui Hu, Zikai Zhang","submitted_at":"2026-07-02T23:16:02Z","abstract_excerpt":"Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing a new attack surface. We study vision token manipulation attack (VTM-Attack) under a black-box man-in-the-middle setting, where an adversary intercepts and manipulates a subset of transmitted vision tokens under a budget constraint. We propose four na\\\"ive attack strategies and an optimization-based token selection me"},"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":"2607.02819","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-02T23:16:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ba27592a3f5294c5ff371ad4c43d175320256dcbbbf5d7bbbd22b2ea3a8dc7a6","abstract_canon_sha256":"327ba3f0922a18327df8ff5a7f9cc6ce5071dd9c2679cf6d854789332ffe2cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:19.020241Z","signature_b64":"P31Hbmv1MvqUPcoj3b8EcTMqBsflxXWk8JEOyiwt1zMc8s9JqgyRMv7mRUCuXgyptkVVp0VYWBJ9dDXGAXWuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04472320700b4c1c205746125cb53e882fad506ac60b62ca846bbfff0309be55","last_reissued_at":"2026-07-07T00:16:19.019572Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:19.019572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CR","authors_text":"Jiahao Xu, Olivera Kotevska, Rui Hu, Zikai Zhang","submitted_at":"2026-07-02T23:16:02Z","abstract_excerpt":"Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing a new attack surface. We study vision token manipulation attack (VTM-Attack) under a black-box man-in-the-middle setting, where an adversary intercepts and manipulates a subset of transmitted vision tokens under a budget constraint. We propose four na\\\"ive attack strategies and an optimization-based token selection me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02819","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/2607.02819/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":"2607.02819","created_at":"2026-07-07T00:16:19.019661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02819v1","created_at":"2026-07-07T00:16:19.019661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02819","created_at":"2026-07-07T00:16:19.019661+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARDSGIDQBNGB","created_at":"2026-07-07T00:16:19.019661+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARDSGIDQBNGBYICX","created_at":"2026-07-07T00:16:19.019661+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARDSGIDQ","created_at":"2026-07-07T00:16:19.019661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA","json":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA.json","graph_json":"https://pith.science/api/pith-number/ARDSGIDQBNGBYICXIYJFZNJ6RA/graph.json","events_json":"https://pith.science/api/pith-number/ARDSGIDQBNGBYICXIYJFZNJ6RA/events.json","paper":"https://pith.science/paper/ARDSGIDQ"},"agent_actions":{"view_html":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA","download_json":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA.json","view_paper":"https://pith.science/paper/ARDSGIDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02819&json=true","fetch_graph":"https://pith.science/api/pith-number/ARDSGIDQBNGBYICXIYJFZNJ6RA/graph.json","fetch_events":"https://pith.science/api/pith-number/ARDSGIDQBNGBYICXIYJFZNJ6RA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA/action/storage_attestation","attest_author":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA/action/author_attestation","sign_citation":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA/action/citation_signature","submit_replication":"https://pith.science/pith/ARDSGIDQBNGBYICXIYJFZNJ6RA/action/replication_record"}},"created_at":"2026-07-07T00:16:19.019661+00:00","updated_at":"2026-07-07T00:16:19.019661+00:00"}