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

Machines01:19

Machines

563
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. One example of a machine is the cutting plier, which is used to cut wires by applying forces to its handles. When equal and opposite forces are exerted on the handles of the cutting plier, they cause the cutting edges to come together and apply equal and opposite reaction forces on the wire, which are greater than the applied forces.
A free-body diagram of the...
563
Machines: Problem Solving II01:30

Machines: Problem Solving II

652
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.
652
Machines: Problem Solving I01:22

Machines: Problem Solving I

701
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...
701
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

489
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
489
Simplified Synchronous Machine Model01:30

Simplified Synchronous Machine Model

759
The Synchronous Machine Model is a fundamental tool in analyzing and ensuring the transient stability of power systems. This model simplifies the representation of a synchronous machine under balanced three-phase positive-sequence conditions, assuming constant excitation and ignoring losses and saturation. The model is pivotal for understanding the behavior of synchronous generators connected to a power grid, particularly during transient events.
In this model, each generator is connected to a...
759
Wind Turbine Machine Models01:24

Wind Turbine Machine Models

576
In the growing field of wind energy, incorporating wind turbine models into transient stability analysis is essential. Induction and synchronous machines are the primary models used, with induction machines being prevalent due to their simplicity and reliability.
Induction machines interact through the rotating magnetic field generated by the stator and the rotor. The key parameter is slip, which is the difference between synchronous speed and rotor speed relative to synchronous speed. Slip is...
576

You might also read

Related Articles

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

Sort by
Same authorSame journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Obinutuzumab versus rituximab-based chemotherapy in high-tumor burden indolent B-cell lymphoma: a real-world comparative study.

Frontiers in immunology·2026
Same author

Sub-parts-per-billion CO<sub>2</sub> Detection based on Dissipative Whispering Gallery Mode Microcavity Sensor.

Nature communications·2026
Same author

Dual-Site Activation of High-Entropy Alloy Electrocatalysts via Ruthenium-Induced Electron Transfer for Alkaline Hydrogen Evolution.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Towards a physics-informed network paradigm with data generation and background noise removal for different distributed acoustic sensing applications.

Light, science & applications·2026
Same author

Polystyrene nanoplastics induce size-associated oxidative-inflammatory stress, hepatic insulin-signaling impairment and metabolic disturbances in normal and diabetic mice.

Biology direct·2026

Related Experiment Video

Updated: Jan 26, 2026

Fluorescent Leakage Assay to Investigate Membrane Destabilization by Cell-Penetrating Peptide
07:33

Fluorescent Leakage Assay to Investigate Membrane Destabilization by Cell-Penetrating Peptide

Published on: December 19, 2020

7.1K

Mitigating sensitive information leakage in LLMs4Code through machine unlearning.

Shanzhi Gu1, Zhaoyang Qu1, Ruotong Geng2

  • 1College of Computer Science and Technology, National University of Defense Technology, Changsha, 410073, Hunan, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 24, 2026
PubMed
Summary
This summary is machine-generated.

Machine unlearning significantly reduces sensitive data leakage in Large Language Models for Code (LLMs4Code), cutting direct leaks by over 50% while preserving 91% of coding ability. Further research is needed to address remaining indirect leakage.

Keywords:
LLMs4CodeLarge language modelMachine unlearningPrivacy leakage

More Related Videos

The C-seal: A Biofragmentable Drain Protecting the Stapled Colorectal Anastomosis from Leakage
07:51

The C-seal: A Biofragmentable Drain Protecting the Stapled Colorectal Anastomosis from Leakage

Published on: November 4, 2010

22.4K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

952

Related Experiment Videos

Last Updated: Jan 26, 2026

Fluorescent Leakage Assay to Investigate Membrane Destabilization by Cell-Penetrating Peptide
07:33

Fluorescent Leakage Assay to Investigate Membrane Destabilization by Cell-Penetrating Peptide

Published on: December 19, 2020

7.1K
The C-seal: A Biofragmentable Drain Protecting the Stapled Colorectal Anastomosis from Leakage
07:51

The C-seal: A Biofragmentable Drain Protecting the Stapled Colorectal Anastomosis from Leakage

Published on: November 4, 2010

22.4K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

952

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Software Engineering

Background:

  • Large Language Models for Code (LLMs4Code) excel at code generation but risk leaking sensitive training data.
  • Existing privacy measures for LLMs4Code are insufficient to prevent sensitive information disclosure.

Purpose of the Study:

  • This study provides the first comprehensive empirical analysis of machine unlearning for mitigating sensitive data leakage in LLMs4Code.
  • To evaluate the effectiveness of machine unlearning in reducing privacy risks while maintaining model performance.

Main Methods:

  • A dedicated benchmark was created with synthetic "forget" and "retain" datasets to test privacy and functionality.
  • Three machine unlearning algorithms (GA, GA+GD, GA+KL) were systematically assessed on three open-source LLMs4Code models (AIXCoder-7B, CodeLlama-7B, CodeQwen-7B).

Main Results:

  • Machine unlearning reduced direct data leakage by over 50% on average.
  • Code-generation performance was retained at over 91% after unlearning.
  • A shift from direct to indirect data leakage was observed post-unlearning, indicating a persistent vulnerability.

Conclusions:

  • Machine unlearning is a viable and effective method for enhancing privacy in LLMs4Code.
  • Future research must develop techniques to address both direct and indirect leakage simultaneously for robust privacy protection.