{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DSEJQBMAZCHPSDQKFKPVEQHUYG","short_pith_number":"pith:DSEJQBMA","canonical_record":{"source":{"id":"2605.14387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T05:11:09Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"1f78b22e06c0cd4ad7f30427a2c4371e156dd55c5baac6b2d7c745b5c831fca1","abstract_canon_sha256":"d4a51a4b50fd6812a32397bf4efc70a221dc5288a7659ba3014501e820592b0f"},"schema_version":"1.0"},"canonical_sha256":"1c88980580c88ef90e0a2a9f5240f4c1aea258cfa71c5512c3679be8444616cb","source":{"kind":"arxiv","id":"2605.14387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14387","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14387v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14387","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"DSEJQBMAZCHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSEJQBMAZCHPSDQK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSEJQBMA","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DSEJQBMAZCHPSDQKFKPVEQHUYG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T05:11:09Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"1f78b22e06c0cd4ad7f30427a2c4371e156dd55c5baac6b2d7c745b5c831fca1","abstract_canon_sha256":"d4a51a4b50fd6812a32397bf4efc70a221dc5288a7659ba3014501e820592b0f"},"schema_version":"1.0"},"canonical_sha256":"1c88980580c88ef90e0a2a9f5240f4c1aea258cfa71c5512c3679be8444616cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.655845Z","signature_b64":"Ed4OTsv0fDqN15UZKZpHAQ+/6nXXObLVyssSF1Y3UWqMiIQ0hsULZt3sI66iwgXQj+1E8QFF4RqDRoZL/WhMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c88980580c88ef90e0a2a9f5240f4c1aea258cfa71c5512c3679be8444616cb","last_reissued_at":"2026-05-17T23:39:07.655187Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.655187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14387","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":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6UBNLjHHIO8NHGtte2NpmP72/GPyo3mNJMmKemhtWdH978sOFFrvdozSQrb4+75TFPNeyi07KPooLN+QnzcHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:55:40.257570Z"},"content_sha256":"e536522d727fffe0acb07b44413e639d6fe12f042fff30c6eb466858fd2537c4","schema_version":"1.0","event_id":"sha256:e536522d727fffe0acb07b44413e639d6fe12f042fff30c6eb466858fd2537c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DSEJQBMAZCHPSDQKFKPVEQHUYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Forensics in AI-Native Wireless Networks: Taxonomy, Applications, and Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Model forensics verifies AI model authenticity and detects tampering in wireless networks.","cross_cats":["eess.SP"],"primary_cat":"cs.CR","authors_text":"Dusit Niyato, Jiacheng Wang, Jin Xu, Ning Wang, Pengyu Chen, Tao Xiang, Weiyang Li","submitted_at":"2026-05-14T05:11:09Z","abstract_excerpt":"As artificial intelligence (AI) is increasingly embedded in wireless networks, models are becoming core components that influence signal processing, resource scheduling and network control. However, model anomalies, tampering and malicious functions also introduce new security risks. In this article, we focus on model forensics in AI-native wireless networks. Specifically, we first discuss key problems including model authenticity verification, malicious function identification and accountability tracing, and summarize the main categories of model forensics. We then explain the role of model f"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The results show that model forensics can provide important support for anomaly assessment, provenance tracing and trustworthy operation in AI-native wireless networks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the watermark authentication and backdoor detection workflows demonstrated in the RF fingerprinting case study can be implemented in real wireless environments without major performance loss or easy circumvention by adversaries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Model forensics offers a taxonomy of techniques for verifying AI model authenticity and detecting malicious functions in wireless networks, with concrete workflows shown in an RF fingerprinting case study to support anomaly assessment and provenance tracing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Model forensics verifies AI model authenticity and detects tampering in wireless networks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2c19d722acca890102c7188d55f50fe88ae52f35fc7205d428ebde1bb6e14094"},"source":{"id":"2605.14387","kind":"arxiv","version":1},"verdict":{"id":"aaead955-f8a6-47d1-8a67-9dba28850036","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:32:46.172266Z","strongest_claim":"The results show that model forensics can provide important support for anomaly assessment, provenance tracing and trustworthy operation in AI-native wireless networks.","one_line_summary":"Model forensics offers a taxonomy of techniques for verifying AI model authenticity and detecting malicious functions in wireless networks, with concrete workflows shown in an RF fingerprinting case study to support anomaly assessment and provenance tracing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the watermark authentication and backdoor detection workflows demonstrated in the RF fingerprinting case study can be implemented in real wireless environments without major performance loss or easy circumvention by adversaries.","pith_extraction_headline":"Model forensics verifies AI model authenticity and detects tampering in wireless networks."},"references":{"count":15,"sample":[{"doi":"","year":2026,"title":"Toward native ai in 6g standardization: The roadmap of semantic communication,","work_id":"13beca3b-94ce-4d85-bc11-f61c5a8d54e8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Overview of ai and communication for 6g network: fundamentals, challenges, and future research opportunities,","work_id":"28f8d66f-9789-443b-8c75-037397de03a1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Towards secure intelligent o-ran architecture: vulnerabilities, threats and promising technical solutions using llms,","work_id":"4179bfeb-f82d-4561-bd2a-206785fccde0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A survey on xai for 5g and beyond security: Technical aspects, challenges and research directions,","work_id":"93f60715-8f09-40d4-8620-457e081ef00f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Founding the domain of ai forensics.,","work_id":"bb081395-f1fd-4e38-bbbe-f0b24d90670d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"eb6814dc151313990865316adaa90a681386bb9cddb5483181f9ba202502e036","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":"aaead955-f8a6-47d1-8a67-9dba28850036"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nCzGGurJO2J36Ifs5BA0AER+3GDR+lMfKPXKh+ibq1Y1qy7Yop9oInvrx/RgEhPJTveTqhf4G0S7WBkgBrdXDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:55:40.258515Z"},"content_sha256":"d1a90aa4a44694c99a8bc34df3ce6b5f21155017af5d7de7783341a75b520b11","schema_version":"1.0","event_id":"sha256:d1a90aa4a44694c99a8bc34df3ce6b5f21155017af5d7de7783341a75b520b11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/bundle.json","state_url":"https://pith.science/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/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":"2026-05-28T06:55:40Z","links":{"resolver":"https://pith.science/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG","bundle":"https://pith.science/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/bundle.json","state":"https://pith.science/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSEJQBMAZCHPSDQKFKPVEQHUYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSEJQBMAZCHPSDQKFKPVEQHUYG","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":"d4a51a4b50fd6812a32397bf4efc70a221dc5288a7659ba3014501e820592b0f","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T05:11:09Z","title_canon_sha256":"1f78b22e06c0cd4ad7f30427a2c4371e156dd55c5baac6b2d7c745b5c831fca1"},"schema_version":"1.0","source":{"id":"2605.14387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14387","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14387v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14387","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"DSEJQBMAZCHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSEJQBMAZCHPSDQK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSEJQBMA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d1a90aa4a44694c99a8bc34df3ce6b5f21155017af5d7de7783341a75b520b11","target":"graph","created_at":"2026-05-17T23:39:07Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The results show that model forensics can provide important support for anomaly assessment, provenance tracing and trustworthy operation in AI-native wireless networks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the watermark authentication and backdoor detection workflows demonstrated in the RF fingerprinting case study can be implemented in real wireless environments without major performance loss or easy circumvention by adversaries."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Model forensics offers a taxonomy of techniques for verifying AI model authenticity and detecting malicious functions in wireless networks, with concrete workflows shown in an RF fingerprinting case study to support anomaly assessment and provenance tracing."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Model forensics verifies AI model authenticity and detects tampering in wireless networks."}],"snapshot_sha256":"2c19d722acca890102c7188d55f50fe88ae52f35fc7205d428ebde1bb6e14094"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"As artificial intelligence (AI) is increasingly embedded in wireless networks, models are becoming core components that influence signal processing, resource scheduling and network control. However, model anomalies, tampering and malicious functions also introduce new security risks. In this article, we focus on model forensics in AI-native wireless networks. Specifically, we first discuss key problems including model authenticity verification, malicious function identification and accountability tracing, and summarize the main categories of model forensics. We then explain the role of model f","authors_text":"Dusit Niyato, Jiacheng Wang, Jin Xu, Ning Wang, Pengyu Chen, Tao Xiang, Weiyang Li","cross_cats":["eess.SP"],"headline":"Model forensics verifies AI model authenticity and detects tampering in wireless networks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T05:11:09Z","title":"Model Forensics in AI-Native Wireless Networks: Taxonomy, Applications, and Case Study"},"references":{"count":15,"internal_anchors":0,"resolved_work":15,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Toward native ai in 6g standardization: The roadmap of semantic communication,","work_id":"13beca3b-94ce-4d85-bc11-f61c5a8d54e8","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Overview of ai and communication for 6g network: fundamentals, challenges, and future research opportunities,","work_id":"28f8d66f-9789-443b-8c75-037397de03a1","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Towards secure intelligent o-ran architecture: vulnerabilities, threats and promising technical solutions using llms,","work_id":"4179bfeb-f82d-4561-bd2a-206785fccde0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A survey on xai for 5g and beyond security: Technical aspects, challenges and research directions,","work_id":"93f60715-8f09-40d4-8620-457e081ef00f","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Founding the domain of ai forensics.,","work_id":"bb081395-f1fd-4e38-bbbe-f0b24d90670d","year":2020}],"snapshot_sha256":"eb6814dc151313990865316adaa90a681386bb9cddb5483181f9ba202502e036"},"source":{"id":"2605.14387","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:32:46.172266Z","id":"aaead955-f8a6-47d1-8a67-9dba28850036","model_set":{"reader":"grok-4.3"},"one_line_summary":"Model forensics offers a taxonomy of techniques for verifying AI model authenticity and detecting malicious functions in wireless networks, with concrete workflows shown in an RF fingerprinting case study to support anomaly assessment and provenance tracing.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Model forensics verifies AI model authenticity and detects tampering in wireless networks.","strongest_claim":"The results show that model forensics can provide important support for anomaly assessment, provenance tracing and trustworthy operation in AI-native wireless networks.","weakest_assumption":"That the watermark authentication and backdoor detection workflows demonstrated in the RF fingerprinting case study can be implemented in real wireless environments without major performance loss or easy circumvention by adversaries."}},"verdict_id":"aaead955-f8a6-47d1-8a67-9dba28850036"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e536522d727fffe0acb07b44413e639d6fe12f042fff30c6eb466858fd2537c4","target":"record","created_at":"2026-05-17T23:39:07Z","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":"d4a51a4b50fd6812a32397bf4efc70a221dc5288a7659ba3014501e820592b0f","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T05:11:09Z","title_canon_sha256":"1f78b22e06c0cd4ad7f30427a2c4371e156dd55c5baac6b2d7c745b5c831fca1"},"schema_version":"1.0","source":{"id":"2605.14387","kind":"arxiv","version":1}},"canonical_sha256":"1c88980580c88ef90e0a2a9f5240f4c1aea258cfa71c5512c3679be8444616cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c88980580c88ef90e0a2a9f5240f4c1aea258cfa71c5512c3679be8444616cb","first_computed_at":"2026-05-17T23:39:07.655187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.655187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ed4OTsv0fDqN15UZKZpHAQ+/6nXXObLVyssSF1Y3UWqMiIQ0hsULZt3sI66iwgXQj+1E8QFF4RqDRoZL/WhMCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.655845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e536522d727fffe0acb07b44413e639d6fe12f042fff30c6eb466858fd2537c4","sha256:d1a90aa4a44694c99a8bc34df3ce6b5f21155017af5d7de7783341a75b520b11"],"state_sha256":"140d51b6561dec6c0ad2fc50b3988b00025820d41062461a8614a02cd7df8c55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QnnsbRBFIVID7AdKvfhxYHzOBKjVqhRglZoe5vhL3VyVfjV9+kNmc4tAgzGJg3QrXKg+5SVVtAOc+BVevtfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T06:55:40.262393Z","bundle_sha256":"22e520840b1f2d5e38b385d739b8b8c392a5ccd1d096b3282712d575d2f9f0c5"}}