DeepAI AI Chat
Log In Sign Up

Analysis and Detectability of Offline Data Poisoning Attacks on Linear Systems

by   Alessio Russo, et al.

A recent body of literature has investigated the effect of data poisoning attacks on data-driven control methods. Data poisoning attacks are well-known to the Machine Learning community, which, however, make use of assumptions, such as cross-sample independence, that in general do not hold for dynamical systems. As a consequence, attacks, and detection methods, operate differently from the i.i.d. setting studied in classical supervised problems. In particular, data poisoning attacks against data-driven control methods can be fundamentally seen as changing the behavior of the dynamical system described by the data. In this work, we study this phenomenon through the lens of statistical testing, and verify the detectability of different attacks for a linear dynamical system. On the basis of the arguments hereby presented, we propose a stealthy data poisoning attack that can escape classical detection tests, and conclude by showing the efficiency of the proposed attack.


page 21

page 25

page 26


Randomized Algorithms for Data-Driven Stabilization of Stochastic Linear Systems

Data-driven control strategies for dynamical systems with unknown parame...

Data-Driven Attack Detection for Linear Systems

This paper studies the attack detection problem in a data-driven and mod...

Data-driven Influence Based Clustering of Dynamical Systems

Community detection is a challenging and relevant problem in various dis...

Linear and non-linear machine learning attacks on physical unclonable functions

In this thesis, several linear and non-linear machine learning attacks o...

On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis

In this work, we study discrete morphological symmetries of dynamical sy...

Code Repositories


Code for the paper Analysis and Detectability of Offline Data Poisoning Attacks on Linear Systems.

view repo