{"paper":{"title":"On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A Swin Transformer semantic communication system with federated learning improves UAV image transmission quality by at least 5.7 dB PSNR while keeping raw data private.","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Dongwei Zhao, Kexin Zhang, Lixin Li, Rui Li, Wensheng Lin, Xin Zhang, Yuna Yan, Zhu Han","submitted_at":"2026-05-12T09:18:53Z","abstract_excerpt":"The rapid development of low-altitude economy has driven the proliferation of Unmanned Aerial Vehicle (UAV) applications, including logistics, inspection, and emergency response. However, transmitting high-volume image data from UAVs to ground stations faces significant challenges due to limited bandwidth and stringent privacy requirements. To address these issues, a Semantic Communication (SC) framework based on Federated Learning (FL) is proposed for efficient and privacy-preserving image transmission. A Swin Transformer-based Semantic Communication (STSC) architecture is designed to extract"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Simulation experiments conducted on the CIFAR-10 dataset demonstrate that the proposed STSC framework achieves at least 5.7 dB improvement in Peak Signal-to-Noise Ratio (PSNR) compared to DeepJSCC baselines, while also showing superior convergence and generalization performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That performance gains measured on the CIFAR-10 dataset under simulated conditions will hold for real UAV deployments facing actual bandwidth limits, channel noise, and privacy regulations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A Swin Transformer-based semantic communication framework with federated learning reports 5.7 dB PSNR gains over DeepJSCC baselines for UAV image transmission on CIFAR-10.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A Swin Transformer semantic communication system with federated learning improves UAV image transmission quality by at least 5.7 dB PSNR while keeping raw data private.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"12b185144fa185c9d8b1b8f2f42db04a9cde0cafdf744095fc150e0d486eb566"},"source":{"id":"2605.12566","kind":"arxiv","version":1},"verdict":{"id":"3dad84aa-71e3-4a92-9726-43ba5c6e2785","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:45:25.535252Z","strongest_claim":"Simulation experiments conducted on the CIFAR-10 dataset demonstrate that the proposed STSC framework achieves at least 5.7 dB improvement in Peak Signal-to-Noise Ratio (PSNR) compared to DeepJSCC baselines, while also showing superior convergence and generalization performance.","one_line_summary":"A Swin Transformer-based semantic communication framework with federated learning reports 5.7 dB PSNR gains over DeepJSCC baselines for UAV image transmission on CIFAR-10.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That performance gains measured on the CIFAR-10 dataset under simulated conditions will hold for real UAV deployments facing actual bandwidth limits, channel noise, and privacy regulations.","pith_extraction_headline":"A Swin Transformer semantic communication system with federated learning improves UAV image transmission quality by at least 5.7 dB PSNR while keeping raw data private."},"references":{"count":41,"sample":[{"doi":"","year":2023,"title":"Rethink- ing modern communication from semantic coding to semantic communication","work_id":"5c0861e7-0581-4f19-b58c-a5fc9057f7db","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Beyond transmitting bits: Context, semantics, and task-oriented communications","work_id":"64958c63-5abd-45da-b31b-338c7cf08dd3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"FSSC: Federated learning of transformer neural networks for semantic image communication","work_id":"ecf5c540-9546-462a-81c5-b1741cbb8c45","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"FLSC-CI: Federated learning and semantic communication empowered multimodal terminal col- laborative inferencing framework for IoT businesses","work_id":"f7e98beb-58a1-4d33-989e-3d76cf1a411b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Federated learning based audio semantic communication over wireless net- works","work_id":"c1fc177c-9c2a-4c7a-82e4-8b609a4bd80b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"b0c7ee5419d7dc7295add5a2796006c66f201d820adcd3031016db3c75ac4368","internal_anchors":2},"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"}