Research map / Continual learning / Continual fine-tuning of LLMs
Source-Free Open-World RF Fingerprint Identification
Kunling Li, Cunqing Hua, Hongyu Zhu, Tianjie Ju, Pengwenlong Gu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add intra-class separation (MaxSep part) to inter-orthogonal geometry (ablation) | IO-ETF · Oracle | new-class accuracy: 80.34 -> 97.30 | Improved |
| add inter-orthogonality to intra-ETF separation (ablation) | IO-ETF · Oracle | gradient leakage: 0.55 -> 0.04 | Improved |
| add inter-orthogonality to intra-ETF separation (ablation) | IO-ETF · Oracle | old-class accuracy: 93.67 -> 96.25 | Improved |
| use IO-ETF instead of global ETF reconstruction (ablation) | output geometry · Oracle | new-class accuracy: 62.92 -> 97.30 | Improved |
| use IO-ETF instead of random anchors (ablation) | output geometry · Oracle | AUROC: 75.22 -> 96.60 | Improved |
| use IO-ETF instead of inter-orthogonal only (ablation) | output geometry · WiSig | new-class accuracy: 84.09 -> 99.75 | Improved |
| add semantic optimal transport (BEOT) (ablation) | TLGA · Oracle | new-class accuracy: 40.41 -> 99.69 | Improved |
| add manifold progressive anchoring (PMA) (ablation) | TLGA · Oracle and WiSig | AUROC: around 14% | Improved |
| add reliability-aware pseudo-replay (RAPR) (ablation) | TLGA · Oracle and WiSig | accuracy: around 5% | Improved |
| use Ours instead of best baseline | SF-OW RFFI · Overall average | H-score: 90.78 -> 97.05 | Improved |
| use Ours instead of SF-OpenLDN | SF-OW RFFI · LoRa | H-score: 80.00 -> 91.36 | Improved |
Closest papers by meaning
- Towards Distance-Invariant Radio Frequency Fingerprinting via Augmented Unsupervised Learning (AAAI 2026 · similarity 0.89)
- Open-world Radio Frequency Fingerprint Identification via Augmented Semi-supervised Learning (AAAI 2025 · similarity 0.88)
- Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models (ICML 2024 · similarity 0.81)
- Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication (AAAI 2024 · similarity 0.80)
- Scalable Fingerprinting of Large Language Models (NeurIPS 2025 · similarity 0.80)
- SIF: Semantically In-Distribution Fingerprints for Large Vision-Language Models (CVPR 2026 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
