{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LZBQIEAOVOKPI5ZMI36OR4GSW3","short_pith_number":"pith:LZBQIEAO","schema_version":"1.0","canonical_sha256":"5e4304100eab94f4772c46fce8f0d2b6f7881cf54b3fc8d519ea48fe93dae2da","source":{"kind":"arxiv","id":"2504.04716","version":1},"attestation_state":"computed","paper":{"title":"On the Robustness of GUI Grounding Models Against Image Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoren Zhao, Tianyi Chen, Zhen Wang","submitted_at":"2025-04-07T03:58:45Z","abstract_excerpt":"Graphical User Interface (GUI) grounding models are crucial for enabling intelligent agents to understand and interact with complex visual interfaces. However, these models face significant robustness challenges in real-world scenarios due to natural noise and adversarial perturbations, and their robustness remains underexplored. In this study, we systematically evaluate the robustness of state-of-the-art GUI grounding models, such as UGround, under three conditions: natural noise, untargeted adversarial attacks, and targeted adversarial attacks. Our experiments, which were conducted across a "},"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":"2504.04716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T03:58:45Z","cross_cats_sorted":[],"title_canon_sha256":"1795ca49da0eb5b33919c82ac6d6b61657f1eceaf481dfa818c1b41280659e1d","abstract_canon_sha256":"2dd4d61c960ebaed0faaa52e04ce2b402c5f4498cae7fed381c61d81cd0e4728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:28.873487Z","signature_b64":"WlXWT8uP2eH4V2xTA26dYxTZ81KO6HPfbRSYmUTOszwcWKDHaWo5LSXH+Xl/dp6o/Kj4mZxy7HbvVbiho3BqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e4304100eab94f4772c46fce8f0d2b6f7881cf54b3fc8d519ea48fe93dae2da","last_reissued_at":"2026-07-05T10:45:28.873007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:28.873007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Robustness of GUI Grounding Models Against Image Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoren Zhao, Tianyi Chen, Zhen Wang","submitted_at":"2025-04-07T03:58:45Z","abstract_excerpt":"Graphical User Interface (GUI) grounding models are crucial for enabling intelligent agents to understand and interact with complex visual interfaces. However, these models face significant robustness challenges in real-world scenarios due to natural noise and adversarial perturbations, and their robustness remains underexplored. In this study, we systematically evaluate the robustness of state-of-the-art GUI grounding models, such as UGround, under three conditions: natural noise, untargeted adversarial attacks, and targeted adversarial attacks. Our experiments, which were conducted across a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04716","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/2504.04716/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":"2504.04716","created_at":"2026-07-05T10:45:28.873057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04716v1","created_at":"2026-07-05T10:45:28.873057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04716","created_at":"2026-07-05T10:45:28.873057+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZBQIEAOVOKP","created_at":"2026-07-05T10:45:28.873057+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZBQIEAOVOKPI5ZM","created_at":"2026-07-05T10:45:28.873057+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZBQIEAO","created_at":"2026-07-05T10:45:28.873057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15259","citing_title":"ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3","json":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3.json","graph_json":"https://pith.science/api/pith-number/LZBQIEAOVOKPI5ZMI36OR4GSW3/graph.json","events_json":"https://pith.science/api/pith-number/LZBQIEAOVOKPI5ZMI36OR4GSW3/events.json","paper":"https://pith.science/paper/LZBQIEAO"},"agent_actions":{"view_html":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3","download_json":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3.json","view_paper":"https://pith.science/paper/LZBQIEAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04716&json=true","fetch_graph":"https://pith.science/api/pith-number/LZBQIEAOVOKPI5ZMI36OR4GSW3/graph.json","fetch_events":"https://pith.science/api/pith-number/LZBQIEAOVOKPI5ZMI36OR4GSW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3/action/storage_attestation","attest_author":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3/action/author_attestation","sign_citation":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3/action/citation_signature","submit_replication":"https://pith.science/pith/LZBQIEAOVOKPI5ZMI36OR4GSW3/action/replication_record"}},"created_at":"2026-07-05T10:45:28.873057+00:00","updated_at":"2026-07-05T10:45:28.873057+00:00"}