Abstract
Federated Learning (FL) over 5G cellular networks protects raw data but remains vulnerable to side-channel leakage. Prior fingerprinting attacks assume packet-level network visibility, an assumption that does not hold at the 5G Physical (PHY) layer, where user payloads are encrypted and Radio Network Temporary Identifiers (RNTIs) may change over time.
However, we demonstrate that PHY-layer scheduling metadata broadcast over the Physical Downlink Control Channel (PDCCH) preserves architecture-associated temporal patterns.
We introduce FLINT, a novel black-box fingerprinting framework that infers FL model architecture families, including CNNs, RNNs, and Transformers, using only coarse PHY-layer observations. FLINT overcomes the lack of network-layer visibility by decoding PDCCH scheduling information, mapping changing RNTIs to physical user devices, and applying multi-view temporal modeling to distinguish architecture-specific training behavior.
This leakage is security-critical because knowledge of a client's model architecture can transform passive reconnaissance into targeted downstream exploitation.
Extensive experiments on an over-the-air srsRAN-based 5G testbed demonstrate that FLINT achieves a macro F1-score of 0.930 for architecture-family classification. To our knowledge, FLINT is the first work to fingerprint AI/ML model architectures using lower-layer 5G side-channel information obtainable by any protocol-aware adversary.
Blogger's Review: The introduction of FLINT highlights new security challenges for federated learning in 5G networks, showcasing the potential of PHY-layer data in model architecture identification. This research not only enriches the security discourse around federated learning but also provides a basis for subsequent defensive measures. As network environments become increasingly complex, researchers in the field need to enhance their defenses against side-channel attacks.