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

Survival Tree01:19

Survival Tree

159
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...
159
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.1K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.8K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.8K
Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

6.4K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.4K
Mismatch Repair01:36

Mismatch Repair

40.6K
Overview
40.6K
¹H NMR: Interpreting Distorted and Overlapping Signals01:02

¹H NMR: Interpreting Distorted and Overlapping Signals

1.1K
Spin systems where the difference in chemical shifts of the coupled nuclei is greater than ten times J are called first-order spin systems. These nuclei are weakly coupled, and their chemical shifts and coupling constant can generally be estimated from the well-separated signals in the spectrum.
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
1.1K

También podría leer

Artículos Relacionados

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

Ordenar por
Same author

Investigating The Causal Effects of Chronic Metabolic Traits on Stroke and The Mediating Role of Depression: Evidence From Mendelian Randomization.

Journal of visualized experiments : JoVE·2026
Same author

Effects of rTMS on swallowing function and neuroimaging features in post-stroke dysphagia.

Frontiers in human neuroscience·2025
Same author

Glutamate dehydrogenase 2 is required for virulence by facilitating fungal growth in the host hemocoel.

Virulence·2025
Same author

Integrating rhythmic auditory stimulation in intelligent rehabilitation technologies for enhanced post-stroke recovery.

Frontiers in bioengineering and biotechnology·2025
Same author

Effectiveness of computer-assisted cognitive training on cognitive function and activities of daily living in patients with post-stroke cognitive impairment.

Frontiers in aging neuroscience·2025
Same author

VDCRL: vulnerability detection with supervised contrastive code representation learning.

Neural networks : the official journal of the International Neural Network Society·2025

Video Experimental Relacionado

Updated: Sep 9, 2025

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

681

Detección de muestras de puerta trasera basada en la consistencia de la discrepancia de perturbación en modelos de

Zuquan Peng1, Jianming Fu1, Lixin Zou1

  • 1Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, 430000, Hubei, China.

Neural networks : the official journal of the International Neural Network Society
|August 31, 2025
PubMed
Resumen

Introducimos un nuevo método de detección de muestras de puerta trasera, la Evaluación de Consistencia de Discrepancia de Perturbación (NETE), que identifica datos maliciosos en modelos previamente entrenados sin necesidad de muestras envenenadas o recursos extensos. NETE detecta efectivamente los ataques de puerta trasera tanto en las fases de entrenamiento como de inferencia.

Palabras clave:
Ataques por la puerta traseraDetección de muestras de puertas traserasCaja negraModelos de lenguaje preformados

Más Videos Relacionados

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

522

Videos de Experimentos Relacionados

Last Updated: Sep 9, 2025

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

681
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

522

Área de la Ciencia:

  • Inteligencia artificial
  • Seguridad del aprendizaje automático

Sus antecedentes:

  • Los modelos pre-entrenados son vulnerables a los ataques de la puerta trasera de los datos no verificados.
  • Los métodos de detección existentes a menudo no son prácticos debido a los requisitos de recursos o acceso.

Objetivo del estudio:

  • Desarrollar un método práctico y eficaz de detección de muestras de puerta trasera.
  • Permitir la detección tanto en las fases previas como posteriores a la formación.

Principales métodos:

  • Proponer una evaluación de la coherencia de las discrepancias de perturbación (NETE).
  • Utilice modelos previamente entrenados y una estrategia de relleno de máscara para las perturbaciones.
  • Medir las discrepancias de probabilidad de registro utilizando la curvatura para evaluar la consistencia.

Principales resultados:

  • NETE aprovecha el fenómeno de que la discrepancia de perturbación cambia menos para las muestras de puerta trasera que para las muestras limpias.
  • El método supera las técnicas de detección de caja negra de disparo cero existentes.
  • Eficacia demostrada contra cuatro ataques típicos de puerta trasera y cinco tipos de ataques de puerta trasera de modelos de lenguaje grandes.

Conclusiones:

  • NETE ofrece una solución práctica para la detección de muestras de puerta trasera.
  • El método es efectivo en varios tipos de ataques y fases de modelo.
  • Mejora la seguridad de los modelos pre-entrenados contra el envenenamiento de datos.