Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements are commercially sensitive, and hand-crafted attacks fail to capture complex distributional structures imposed by network physics. We present \textsc{GenAI-FDIA}, a framework benchmarking a pool of
P=20 architectures for physics-compliant FDIA synthesis, spanning Wasserstein GANs, MMD-VAEs, normalising flows, diffusion models, and cross-family hybrids. These are evaluated across three IEEE testbeds (14-bus DC, 30-bus DC, and 14-bus AC) under a 60/20/20 chronological split using data-driven Bad Data Detection (BDD) threshold calibration. Our empirical results verify that these models generate high-fidelity attacks, with all architectures achieving evasion rates of
εBDD≥86.6% on the 14-bus network; additionally, limiting an attacker's topological knowledge induces a measurable degradation in stealthiness (
p≤0.0022). Crucially, we identify a previously unreported failure mode: applying affine physics projections directly in normalised feature spaces critically displaces the attack vector, collapsing BDD evasion from
∼55% to
<2% on the 30-bus testbed. We resolve this via a novel inference-time harmoniser, restoring full stealthiness (
εBDD=100%) across all physics-informed variants without retraining. Finally, we isolate a covariance-collapse phenomenon (
κ≈−0.076) within advanced hybrid architectures and rectify it through 50-epoch warm-up schedules (
κ→0.785,
ΔMMD=−3.1%). Ultimately, \textsc{GenAI-FDIA} delivers a robust recovery blueprint applicable to any physics-constrained generative model deployed for power-system security.
Mohammad A. Razzaque, Muta Tah Hira