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

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

21.1K
Here, we present a protocol to quantify nest building behavior in mice, which is known to be impaired in several neurological disorders and diseases. This protocol examines the utility of four materials and offers the opportunity to quantify the rater agreement in scoring, improving the validity and reliability of the...
21.1K
Self-Evaluation: Self-Enhancement and Self-Verification03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.7K
Indicators02:39

Indicators

59.4K
Certain organic substances change color in dilute solution when the hydronium ion concentration reaches a particular value. For example, phenolphthalein is a colorless substance in any aqueous solution with a hydronium ion concentration greater than 5.0 × 10−9 M (pH < 8.3). In more basic solutions where the hydronium ion concentration is less than 5.0 × 10−9 M (pH > 8.3), it is red or pink. Substances such as phenolphthalein, which can be used to determine the pH of a solution, are...
59.4K
Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

8.1K
Here, we present a protocol to establish a replicable conductive hearing loss induction via surgical tympanic membrane puncture and verification by otoscope visualization and behavioral assessment by clap...
8.1K
Strategies of Self-Presentation II: Self-Verification01:17

Strategies of Self-Presentation II: Self-Verification

174
Self-verification is a fundamental psychological drive wherein individuals seek affirmation of their self-concept from others, striving for consistency between their internal self-view and external perceptions. This drive operates even when the self-concept is negative, influencing interpersonal behavior and feedback preferences in complex and often counterintuitive ways. Unlike the self-enhancement motive, which seeks positive evaluations, self-verification prioritizes coherence and...
174
Behavioral Characterization of an Angelman Syndrome Mouse Model11:05

Behavioral Characterization of an Angelman Syndrome Mouse Model

5.7K
This manuscript presents a set of highly reproducible behavioral tests to validate an Angelman syndrome mouse...
5.7K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Is a Win-Win possible? Achieving pareto-optimal privacy-utility balance in fine-tuned genome language model embeddings against embedding reconstruction attacks.

Bioinformatics (Oxford, England)·2026
Same author

PROVGEN: A Privacy-Preserving Approach for Outcome Validation in Genomic Research.

Proceedings on Privacy Enhancing Technologies. Privacy Enhancing Technologies Symposium·2026
Same author

Privacy-Preserving Collaborative Population Stratification with Dynamic Algorithm and Hyperparameter Selection.

ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine·2026
Same author

Privacy-preserving verification of preprocessing in federated learning for genomic data.

JAMIA open·2026
Same author

Explainable drug side effect prediction in central neural system via biologically informed graph neural network.

Translational psychiatry·2026
Same author

Semantically Correct Policy Mining and Enforcement for Attribute based Access Control.

ACM transactions on Internet technology·2026

Video Experimental Relacionado

Updated: Jan 20, 2026

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice
06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

Published on: October 19, 2019

21.1K

Verificación de la Preprocesamiento de ML con Preservación de la Privacidad mediante Indicadores de Comportamiento

Wenbiao Li1, Anisa Halimi2, Jaideep Vaidya3

  • 1Case Western Reserve University, Cleveland, OH 44106 USA.

IEEE transactions on privacy
|January 19, 2026
PubMed
Resumen

Desarrollamos un método de preservación de la privacidad para verificar el preprocesamiento de datos de aprendizaje automático. Este enfoque utiliza el análisis del comportamiento del modelo para garantizar la integridad de la canalización sin necesidad de datos originales o etiquetas.

Palabras clave:
preprocesamiento de datosprivacidad diferencialIA explicableprivacidad diferencial localauditoría de modelosdatos tabulares

Más Videos Relacionados

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat
06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

Published on: October 26, 2019

8.1K
Self-Evaluation: Self-Enhancement and Self-Verification
03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K

Videos de Experimentos Relacionados

Last Updated: Jan 20, 2026

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice
06:11

Nest Building Behavior as an Early Indicator of Behavioral Deficits in Mice

Published on: October 19, 2019

21.1K
Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat
06:27

Simple Surgical Induction of Conductive Hearing Loss with Verification Using Otoscope Visualization and Behavioral Clap Startle Response in Rat

Published on: October 26, 2019

8.1K
Self-Evaluation: Self-Enhancement and Self-Verification
03:00

Self-Evaluation: Self-Enhancement and Self-Verification

5.7K

Área de la Ciencia:

  • Aprendizaje Automático
  • Privacidad de Datos
  • Verificación de Modelos

Sus antecedentes:

  • Garantizar la integridad del preprocesamiento de datos es crucial para la confiabilidad del modelo de aprendizaje automático, especialmente con datos sensibles.
  • Los métodos existentes a menudo requieren acceso a datos u etiquetas originales, lo que limita su aplicabilidad en escenarios de preservación de la privacidad.

Objetivo del estudio:

  • Introducir un marco novedoso de preservación de la privacidad para verificar la aplicación correcta de las canalizaciones de preprocesamiento de datos.
  • Permitir la verificación del modelo utilizando solo acceso de caja negra al modelo entrenado, sin datos de entrenamiento originales o etiquetas de referencia.

Principales métodos:

  • El marco combina tres indicadores de comportamiento: cambios en la precisión de la predicción, divergencia de Kullback-Leibler (KL) de las distribuciones de salida y vectores de explicación (LIME/SHAP).
  • Admite decisiones de corrección binaria y diagnóstico de múltiples clases de pasos de preprocesamiento faltantes.
  • Una variante sin etiquetas utiliza la agrupación de vectores de explicación para la verificación.

Principales resultados:

  • El detector binario logró una puntuación F1 superior al 75% incluso bajo una fuerte privacidad diferencial local (ε=0.1).
  • Los clasificadores de aprendizaje automático superaron a las reglas de umbral simples para tareas de clasificación binaria.
  • Se observó un rendimiento comparable entre los clasificadores y las reglas de umbral para el diagnóstico de múltiples clases.

Conclusiones:

  • El marco propuesto ofrece una solución práctica y escalable para salvaguardar la integridad del preprocesamiento en el aprendizaje automático sensible a la privacidad.
  • El método verifica eficazmente las canalizaciones de preprocesamiento sin comprometer la privacidad de los datos ni requerir un acceso extensivo a los datos.
  • La variante sin etiquetas amplía la aplicabilidad del método de verificación a escenarios que carecen de ejemplos de canalización etiquetados.