Apr 23, 2024 · To take into account the security issue in online optimization, this paper investigates the effect of randomly corrupted attacks, which can ...

To take into account the security issue in online optimization, this paper investigates the effect of randomly corrupted attacks, which can corrupt gradient ...

May 1, 2024 · Abstract—Existing algorithms in online optimization usually rely on trustful information, e.g., reliable knowledge of gradients,.

Abstract ; Publication: IEEE Transactions on Signal Processing ; Pub Date: 2024 ; DOI: 10.1109/TSP.2024.3392361 ; Bibcode: 2024ITSP...72.2160Q.

Online Optimization Under Randomly Corrupted Attacks ; A survey of decision making in adversarial games. Li X., Meng M., Hong Y., Chen J. · Q1. Springer Nature.

We study the stability properties of a control system composed of a dynamical plant and a feed- back controller, the latter generating control signals that ...

In this paper, we propose a first-order distributed optimization algorithm that is provably robust to Byzantine failures–arbitrary and potentially ...

Aug 8, 2024 · rounds, we formulate the attack as an online optimization problem, over T corruption patterns, one for each inference round, and the ...

Therefore, it is essential to design efficient online learning algorithms to robustly learn from potentially disrupted behaviors and detect corrupted users in ...

This paper frames the attack problem as an online optimization problem consisting of adversarial example generation (AEG) and corruption pattern selection (CPS) ...