Skip to main content
Search

# Cyber-Physical Systems

1 related articles

Subscribe to updates
  1. arXiv

    Defenders poison the eavesdropped signal: gradient perturbations inflate an attacker's system-identification error while touching only a quarter of transient samples

    Against adversaries that identify a plant with a neural network and then act covertly, a defender injects small perturbations into the measurements the attacker eavesdrops, in decoy settings, so the learned plant model loses accuracy. The perturbations aggregate input gradients from several independently trained models and are confined to transients after setpoint changes. On a simulated DC-motor networked control benchmark, at equal root-mean-square magnitude they produce larger maximum absolute error than Gaussian and pseudo-random binary sequence poisoning, with the gap generally widening as magnitude grows; keeping only 25% of transient samples remains effective.

You’re all caught up