When Does a Neural Receiver Help? Calibration-Drift Benchmarking and Detect-and-Rollback for 5G/6G NR

Collection of recent wireless/communications papers with several security-relevant implications. Key items: (1) neural receivers (DeepRx) outperform classical detectors in-distribution but exhibit brittle behavior under transmitter/channel calibration drift; authors propose detect-and-rollback mitigation—implications for adversarial/operational degradation and denial-of-service against learned PHY. (2) Adversarial Water-Filling (AWF) frames worst‑case interference as a minimax problem (LEO satellite spectrum sharing); provides algorithms and a learned foundation-model/GNN to approximate search