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 Concept Videos

Masking and Demasking Agents01:19

Masking and Demasking Agents

EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on the metal...
Distribution Reliability and Automation01:25

Distribution Reliability and Automation

Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
Machines: Problem Solving II01:30

Machines: Problem Solving II

Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
Reinforcement01:23

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:
Machines: Problem Solving I01:22

Machines: Problem Solving I

A toggle clamp is a mechanical device commonly used for holding and clamping objects in various applications, such as woodworking, metalworking, and assembly operations. Consider a toggle clamp subjected to a force of 200 N at the handle. The vertical clamping force can be calculated, provided the dimensions of the toggle clamp are known.
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
Control System Problem01:21

Control System Problem

In an open-loop system, such as a basic thermostat, the poles of the transfer function influence the system's response but do not determine its stability. However, when feedback is introduced to form a closed-loop system, such as an advanced thermostat that adjusts heating based on room temperature, stability is governed by the new poles of the closed-loop transfer function.
When forming a closed-loop system, issues can arise if the poles cross into the unstable region, leading to potential...

You might also read

Related Articles

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

Sort by
Same author

A Lightweight ScaleDense-Transformer Framework with Auxiliary Quantum-Inspired Bottleneck Module for Whole-Lifespan Brain Age Prediction.

Brain sciences·2026
Same author

From Infancy to Aging: Precise Brain Age Estimation via Hybrid CoTResNet3D and CrossViT Models on T1-Weighted Imaging.

Bioengineering (Basel, Switzerland)·2026
Same author

Brain Age as a Biomarker in Alzheimer's Disease: Narrative Perspectives on Imaging, Biomarkers, Machine Learning, and Intervention Potential.

Brain sciences·2026
Same author

Non-Invasive Blood Pressure Estimation Enhanced by Capillary Refill Time Modulation of PPG Signals.

Sensors (Basel, Switzerland)·2026
Same author

Regional Brain Aging Disparity Index: Region-Specific Brain Aging State Index for Neurodegenerative Diseases and Chronic Disease Specificity.

Bioengineering (Basel, Switzerland)·2025
Same author

Investigating Modifiable Factors Associated with Cognitive Decline: Insights from the UK Biobank.

Biomedicines·2025
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Videos

SafeCodeRL: Security-Constrained Multi-Agent Reinforcement Learning for Trustworthy LLM-Generated IoT/CPS Software.

Zhihua Wang1, Junfan Chen1, Zixiang Wei1

  • 1School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, 516 Jungong Road, Shanghai 200093, China.

Sensors (Basel, Switzerland)
|June 12, 2026
PubMed
Summary
This summary is machine-generated.

SafeCodeRL enhances AI-generated IoT/CPS software security by using multi-agent collaboration and constrained reinforcement learning. This framework significantly reduces vulnerabilities while maintaining functional correctness in code generation.

Keywords:
IoT securityconstrained reinforcement learningcyber-physical systemsedge computinglarge language modelsmulti-agent systemssecure code generationsensor networkssoftware vulnerability mitigationtrustworthy AI

Related Experiment Videos

Area of Science:

  • Cyber-Physical Systems
  • Artificial Intelligence
  • Software Engineering

Background:

  • Large language models (LLMs) and autonomous agents are increasingly used for developing Internet of Things (IoT) and cyber-physical system (CPS) software.
  • LLM-generated code can introduce critical security vulnerabilities like SQL injection and unsafe device control, compromising system integrity and safety.
  • Current security analysis methods are often post hoc and lack a unified approach to balance functionality and security during code generation.

Purpose of the Study:

  • To propose SafeCodeRL, a novel framework for trustworthy AI-assisted software development in IoT/CPS environments.
  • To address the challenge of ensuring security in LLM-generated code through integrated multi-agent collaboration and constrained reinforcement learning.
  • To enable a principled trade-off between software functionality and security in AI-driven code generation.

Main Methods:

  • Modeled code generation as a security-aware sequential decision process involving five agents: Planner, Code, Security, Test, and Critic.
  • Developed a constraint-aware policy using Proximal Policy Optimization, enhanced with a Lagrangian mechanism and shielding strategy for explicit security enforcement.
  • Utilized multi-agent collaboration for joint optimization of task decomposition, code synthesis, vulnerability auditing, and sandbox-based validation.

Main Results:

  • Reduced high-risk vulnerabilities in LLM-generated IoT/CPS software by over 60% across benchmarks like SWE-bench, SecurityEval, and CyberSecEval.
  • Maintained high functional correctness of the generated software.
  • Demonstrated substantial improvement in secure pass rates for critical IoT/CPS tasks, including sensor telemetry and edge gateway management.

Conclusions:

  • SafeCodeRL offers a practical and effective approach to developing secure AI-assisted software for sensor-driven IoT/CPS systems.
  • The framework provides a viable path towards trustworthy AI-generated code by integrating security considerations directly into the generation process.
  • SafeCodeRL successfully balances the need for advanced AI capabilities with robust security guarantees in critical infrastructure software.