LoDiSS: Learning in Low-Dimensional Seeded Subspaces for Long-Term Test-Time Recovery of Floating-Point Neural Weights

As machine learning models are increasingly deployed on standalone edge devices, their weights are exposed to random and adversarial bit flips that can accumulate over time. Most defenses target integer weights or tolerate corruption without repair, leaving floating-point deployment insufficiently protected. Prior real-valued weight recovery suffers from inefficient training and recovery due to redundant variables and group-wide optimization, while inadequate handling of rounding and nonfinite values can lead to unreliable recovery. We introduce LoDiSS, which learns equivalent recoverable weights in low-dimensional seeded subspaces with less training state. Shared pseudorandom transformations efficiently regenerate recovery constraints at test time, while calibrated iterative recovery handles rounding and nonfinite values and reconstructs only suspected weights, without training data or a clean model copy. Across 20 classification settings, LoDiSS retains approximately 100% of clean accuracy under repeated random faults and outperforms baselines under adversarial and recovery-aware adaptive attacks, with mean training and recovery speedups of $2.11\times$ and $17.59\times$ over the existing baseline. Together with evaluations across additional tasks, these results demonstrate reliable, efficient, and task-agnostic floating-point recovery for long-term standalone deployment.