Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K
Censoring Survival Data01:09

Censoring Survival Data

518
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
518
Survival Tree01:19

Survival Tree

382
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
382
Associative Learning01:27

Associative Learning

1.2K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.2K
Masking and Demasking Agents01:19

Masking and Demasking Agents

3.4K
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...
3.4K
Introduction to Learning01:18

Introduction to Learning

923
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
923

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Case Report: A case of acute anterior wall myocardial infarction caused by stent fracture in the left anterior descending artery.

Frontiers in cardiovascular medicine·2026
Same author

Synergistic enhancement mechanism of biochar from Chinese medicine residue for tetracycline hydrochloride removal.

Journal of environmental management·2026
Same author

DIC-DDA: Learned Asymmetric Distributed Image Compression via Dual Domain Alignment.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Unambiguous chromosome identification by multicolour fluorescence in situ hybridisation reveals the genome organisation and evolution of sheepgrass (Leymus chinensis).

BMC plant biology·2026
Same author

Application of high-intensity focused ultrasound in gynaecological diseases.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·2026
Same author

Comparison of the plastisphere and surrounding waste in landfills: Bacterial community assembly and functional evolution.

Journal of environmental management·2025

Video Experimental Relacionado

Updated: Jan 14, 2026

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
06:20

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

3.2K

ARMOR: Protección de ejemplos no aprendibles contra laaugmentation de datos

Xueluan Gong, Yuji Wang, Yanjiao Chen

    IEEE transactions on pattern analysis and machine intelligence
    |January 12, 2026
    PubMed
    Resumen

    Laaugmentation de datos puede comprometer datos privados protegidos por ejemplos no aprendibles, lo que permite a las redes neuronales profundas (DNN) aprender información sensible. El marco ARMOR defiende eficazmente contra estas violaciones de privacidad, asegurando que los datos permanezcan no aprendibles incluso después de laaugmentation. Los ejemplos no aprendibles son ejemplos de datos que se han modificado para que los modelos de aprendizaje profundo no puedan aprender de ellos.

    Palabras clave:
    ARMORejemplos no aprendiblesprivacidad de datosaugmentation de datosredes neuronales profundasdefensa contra la privacidad

    Más Videos Relacionados

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    1.0K
    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    1.3K

    Videos de Experimentos Relacionados

    Last Updated: Jan 14, 2026

    Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
    06:20

    Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

    Published on: December 6, 2024

    3.2K
    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    1.0K
    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
    05:47

    Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

    Published on: June 13, 2025

    1.3K

    Área de la Ciencia:

    • Ciencias de la Computación
    • Inteligencia Artificial
    • Privacidad de Datos

    Sus antecedentes:

    • Los datos privados en línea son vulnerables a la recopilación no autorizada para entrenar redes neuronales profundas (DNN).
    • Los ejemplos no aprendibles tienen como objetivo proteger los datos minimizando la pérdida de entrenamiento de DNN, lo que dificulta el aprendizaje de los datos.
    • Laaugmentation de datos, un paso común de preprocesamiento, puede restaurar inadvertidamente la privacidad en los datos protegidos.

    Objetivo del estudio:

    • Investigar y revelar los riesgos de violación de la privacidad introducidos por laaugmentation de datos en ejemplos no aprendibles.
    • Proponer un marco de defensa novedoso, ARMOR, contra las violaciones de privacidad inducidas por laaugmentation de datos.
    • Desarrollar métodos para defender la privacidad de los datos sin acceso directo al proceso de entrenamiento del modelo.

    Principales métodos:

    • Se diseñó un modelo sustituto asistido por módulos no locales para simular los efectos de laaugmentation de datos.
    • Se desarrolló una estrategia de selección deaugmentation sustituta para optimizar laaugmentation para cada clase.
    • Se utilizó un algoritmo de ajuste de tamaño de paso dinámico para generar ruido defensivo.
    • Se realizaron experimentos exhaustivos en 4 conjuntos de datos y 5 métodos deaugmentation.

    Principales resultados:

    • Laaugmentation de datos aumentó significativamente la precisión del modelo en ejemplos no aprendibles del 21,3% al 66,1%.
    • ARMOR preservó con éxito la no aprendibilidad de los datos privados protegidos contra laaugmentation de datos.
    • ARMOR redujo la precisión de la prueba hasta en un 60% más que los métodos de referencia.
    • El marco de defensa propuesto demostró solidez frente al entrenamiento adversario.

    Conclusiones:

    • Laaugmentation de datos representa una amenaza significativa para la privacidad cuando se aplica a datos no aprendibles.
    • El marco ARMOR proporciona un mecanismo de defensa eficaz contra estas vulnerabilidades de privacidad.
    • ARMOR ofrece una solución robusta para proteger los datos privados en las canalizaciones de aprendizaje automático, incluso con técnicas de preprocesamiento complejas.