Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks
Year: 2025
Type: preprint
Abstract: System identification in modern engineering systems faces emerging challenges from unanticipated adversarial attacks beyond existing detection mechanisms. In this work, we obtain a provably accurate estimate of the Markov parameter matrix of order $k$ to identify partially observed linear systems, in which the probability of having an attack at each time is $O(1/k)$. We show that given the batch data accumulated up to time $T^*$, the $\ell_2$-norm estimator achieves an error decaying exponentially as $k$ grows. We then propose a stochastic projected subgradient descent algorithm on streaming data that produces an estimate at each time $t
Source: arXiv (Cornell University)
Authors: Kim, Jihun, Lavaei, Javad
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414738195
Cites:
Cited by:
Related to: