Bridging Batch and Streaming Estimations to System Identification under Adversarial Attacks
math.OC, cs.SY, eess.SY
Submitted: 2025-09-19
Updated: 2026-11-05
Comments: 16 pages, 2 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: System identification in modern engineering systems faces emerging challenges from unanticipated adversarial attacks beyond existing detection mechanisms.
Terminology
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 p of having an attack at each time is smaller than 0.5. We show that given the batch data accumulated up to time T*, the 2-norm estimator achieves an error with stepwise exponential decay as the attack probability p decreases. Furthermore, low-dimensional attack structures can decouple the exponential decay order from the attack probability p, achieving an error decay that scales with T*. We then propose a stochastic projected subgradient descent algorithm on streaming data that produces an estimate at each time t<T*, in which case the expected estimation error proves to be the larger of O(k/sqrt t) and the baseline error of the 2-norm estimator at T*. This stochastic approach illustrates how non-smooth estimators can leverage first-order methods despite lacking recursive formulas. Finally, we integrate batch and streaming estimations to recover the Hankel matrix using the appropriate estimates of the Markov parameter matrix, which enables the synthesis of a robust adaptive controller based on the estimated balanced truncated model under adversarial attacks.
Sources
- System Identification from Partial Observations under Adversarial Attacks
- On the Sharp Input-Output Analysis of Nonlinear Systems under Adversarial Attacks
- Subgradient Method for System Identification with Non-Smooth Objectives
- Revisiting the Geometrically Decaying Step Size: Linear Convergence for Smooth or Non-Smooth Functions
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise