cs.LGNov 8, 2026

Data Manipulation Attacks Against Machine Learning Integrated Cyber-Physical Systems

Authors: Soyon Choi, Scott Alfeld, Meiyi Ma

Organizations: Department of Computer Science, Vanderbilt University, Nashville, TN · Department of Computer Science, Amherst College, Amherst, MA

Abstract

There is a well-established body of work demonstrating that individual machine learning (ML) algorithms can be manipulated or deceived. However, in many real-world systems, multiple ML algorithms are composed to enable automated decision-making, particularly in Cyber-Physical Systems (CPS). Often such systems use a composition of vision, planning, and other ML models to affect their internal state and ultimate take actions in the physical world. While there is a huge literature on the (in)security of ML algorithms, it is not immediately clear how an attacker might leverage their ability to trick individual learners when attacking the composition as a whole. We develop methods for creating an attack policy (a mapping from state to attack) for a data-manipulating attacker affecting a CPS or other state-machine-based AI compositions. We describe our framework, a basic threat model and corresponding methods for computing an optimal attack policy, as well as planned extensions. The goal of this work-in-progress paper is to stimulate conversation and forge new collaborations regarding the security of compositional learning.

Figures & tables

Explore similar work

CardsList
  1. SMSI: System Model Security Inference: Automated Threat Modeling for Cyber-Physical Systems

    Apr 26, 2026RoÝah Radaideh, Ali KhreisCyber-Physical SystemsCybersecurity

  2. LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems

    Sep 29, 2026Ziyan An, John Stankovic, Meiyi MaCyber-Physical SystemsTime Series Forecasting