Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Adaptive utility-aware event-triggered reinforcement learning for hybrid attack scheduling against remote state

Jieyao An1, Heng Zhang1

  • 1College of Computer Engineering, Jiangsu Ocean University, Lianyungang, Jiangsu 222005, China.

ISA Transactions
|July 6, 2026
PubMed
Summary

Related Concept Videos

Reinforcement Schedules01:24

Reinforcement Schedules

Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Impact of short-term temperature variability on emergency hospital admissions for schizophrenia stratified by season of birth.

International journal of biometeorology·2016
Same author

Design, Synthesis, and Evaluation of Thiophene[3,2-d]pyrimidine Derivatives as HIV-1 Non-nucleoside Reverse Transcriptase Inhibitors with Significantly Improved Drug Resistance Profiles.

Journal of medicinal chemistry·2016
Same author

Rationale and design of a randomized cluster trial to improve guideline-adherence of secondary preventive drugs prescription after coronary artery bypass grafting in China: Measurement and Improvement Studies of Surgical Coronary Revascularization: Secondary Prevention (MISSION-1) Study.

American heart journal·2016
Same author

Exenatide treatment increases serum irisin levels in patients with obesity and newly diagnosed type 2 diabetes.

Journal of diabetes and its complications·2016
Same author

AMPK-dependent regulation of GLP1 expression in L-like cells.

Journal of molecular endocrinology·2016
Same author

Multiprotein-bridging factor 1 regulates vegetative growth, osmotic stress, and virulence in Magnaporthe oryzae.

Current genetics·2016

This study introduces a novel reinforcement learning framework for scheduling hybrid attacks on remote state estimation systems. The event-triggered approach enhances security by adapting to dynamic wireless environments and optimizing attacker resource usage.

Area of Science:

  • Cyber-Physical Systems (CPSs)
  • Network Security
  • Wireless Communication

Background:

  • Remote state estimation is crucial for CPSs but vulnerable to eavesdropping and Denial-of-Service (DoS) attacks.
  • Time-varying wireless channels introduce dynamic security risks, rendering static attack models inadequate.
  • Existing security measures struggle with adaptive and resource-aware attack strategies in dynamic environments.

Purpose of the Study:

  • To develop a utility-aware, event-triggered reinforcement learning framework for hybrid attack scheduling.
  • To address security vulnerabilities in remote state estimation over time-varying wireless channels.
  • To enable attackers to dynamically balance estimation disruption, information acquisition, and resource consumption.

Main Methods:

Keywords:
Cyber-physical systemsDenial-of-serviceEavesdroppingEvent-triggered controlHybrid attackReinforcement learning

Related Experiment Videos

  • Formulated the hybrid attack scheduling as a partially observable Markov decision process (POMDP).
  • Designed a utility-aware event-triggered mechanism to activate attack decisions based on estimated utility.
  • Employed Proximal Policy Optimization (PPO) to learn an adaptive hybrid attack mode selection policy.
  • Analyzed the structural properties of the learned policy, including its piecewise constant structure and monotone triggering property.

    • Main Results:

    • The proposed framework achieved a superior trade-off between remote estimation degradation, attacker information acquisition, and energy consumption compared to benchmarks.
    • The event-triggered reinforcement learning approach demonstrated improved adaptability and resource efficiency in hybrid attack scheduling.
    • Simulation results in a connected vehicle platoon scenario validated the framework's effectiveness.

    Conclusions:

    • The developed framework offers an effective solution for adaptive hybrid attack scheduling in dynamic wireless environments.
    • The study provides valuable insights for enhancing security assessments and designing resilient estimation systems.
    • The findings contribute to the development of robust defense strategies for networked CPSs facing sophisticated cyber threats.