Settle time performance comparisons of stable approximate model inversion techniques

Author(s):  
B.P. Rigney ◽  
L.Y. Pao ◽  
D.A. Lawrence

Author(s):  
Molong Duan ◽  
Keval S. Ramani ◽  
Chinedum E. Okwudire

This paper proposes an approach for minimizing tracking errors in systems with non-minimum phase (NMP) zeros by using filtered basis functions. The output of the tracking controller is represented as a linear combination of basis functions having unknown coefficients. The basis functions are forward filtered using the dynamics of the NMP system and their coefficients selected to minimize the errors in tracking a given trajectory. The control designer is free to choose any suitable set of basis functions but, in this paper, a set of basis functions derived from the widely-used non uniform rational B-spline (NURBS) curve is employed. Analyses and illustrative examples are presented to demonstrate the effectiveness of the proposed approach in comparison to popular approximate model inversion methods like zero phase error tracking control.





2009 ◽  
Vol 113 (12) ◽  
pp. 2560-2573 ◽  
Author(s):  
Jan Stuckens ◽  
Willem W. Verstraeten ◽  
Stephanie Delalieux ◽  
Rony Swennen ◽  
Pol Coppin


2020 ◽  
Vol 2020 (3) ◽  
pp. 264-283
Author(s):  
Seira Hidano ◽  
Takao Murakami ◽  
Shuichi Katsumata ◽  
Shinsaku Kiyomoto ◽  
Goichiro Hanaoka

AbstractPrivacy risks of collaborative filtering (CF) have been widely studied. The current state-of-theart inference attack on user behaviors (e.g., ratings/purchases on sensitive items) for CF is by Calandrino et al. (S&P, 2011). They showed that if an adversary obtained a moderate amount of user’s public behavior before some time T, she can infer user’s private behavior after time T. However, the existence of an attack that infers user’s private behavior before T remains open. In this paper, we propose the first inference attack that reveals past private user behaviors. Our attack departs from previous techniques and is based on model inversion (MI). In particular, we propose the first MI attack on factorization-based CF systems by leveraging data poisoning by Li et al. (NIPS, 2016) in a novel way. We inject malicious users into the CF system so that adversarialy chosen “decoy” items are linked with user’s private behaviors. We also show how to weaken the assumption made by Li et al. on the information available to the adversary from the whole rating matrix to only the item profile and how to create malicious ratings effectively. We validate the effectiveness of our inference algorithm using two real-world datasets.



2010 ◽  
Vol 10 (10) ◽  
pp. 1637-1646 ◽  
Author(s):  
Shyam Sivaramakrishnan ◽  
Rajesh Rajamani ◽  
Bruce D. Johnson






Sign in / Sign up

Export Citation Format

Share Document