Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Avoidance Learning and Learned Helplessness

Avoidance Learning and Learned Helplessness

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...

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...

Survival Tree

Survival Tree

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...

Associative Learning

Associative Learning

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...

Purposive Learning

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...

Self-Evaluation: Self-Enhancement and Self-Verification

Self-Evaluation: Self-Enhancement and Self-Verification

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...

You might also read

Related Articles

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

Sort by

Same author

Cluster-Assembled Hollow SnO<sub>2</sub> Spheres as Biomimetic Enzymes for Ultrasensitive Electrochemical Detection of Superoxide Anions.

ACS omega·2026

Same author

Synchronized UAV multi-angle inversion of canopy structure parameters in wheat breeding materials.

Plant phenomics (Washington, D.C.)·2026

Same author

METTL3 suppresses pyroptosis in obstructive sleep apnea-associated hypertension via YTHDF2-mediated SOX4 mRNA degradation.

Journal of physiology and biochemistry·2026

Same author

LKB1 inactivation elicits an NNMT-mediated methyl sink and confers dependence on PRMT5 in lung cancer.

Cell reports·2026

Same author

Impact of anterior cruciate ligament and medial collateral ligament injuries on medial unicompartmental knee arthroplasty outcomes.

Cirugia y cirujanos·2026

Same author

Wall-associated kinase-like4 regulates plant salt tolerance by maintaining cell wall pectin homeostasis and cellular redox homeostasis in Arabidopsis.

Plant molecular biology·2026

Search research articles

Related Experiment Video

Updated: Jul 16, 2025

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

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

Published on: December 6, 2024

Boosting adversarial robustness via self-paced adversarial training.

Lirong He¹, Qingzhong Ai², Xincheng Yang²

¹School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China; School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.

Neural Networks : the Official Journal of the International Neural Network Society

|September 20, 2023

Summary

This summary is machine-generated.

Self-paced adversarial training (SPAT) enhances deep neural network robustness by gradually introducing complex adversarial examples. This method improves performance and mitigates overfitting and catastrophic forgetting in adversarial training.

Keywords:

Adversarial robustness Adversarial training Self-paced learning

More Related Videos

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

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

Published on: June 13, 2025

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

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

Published on: August 9, 2024

Related Experiment Videos

Last Updated: Jul 16, 2025

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

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

Published on: December 6, 2024

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

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

Published on: June 13, 2025

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

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

Published on: August 9, 2024

Area of Science:

Deep Learning
Machine Learning Security
Computer Vision

Background:

Adversarial training is crucial for deep neural network (DNN) adversarial robustness.
Existing methods like curriculum learning face challenges such as lack of quantitative attack criteria and catastrophic forgetting.
These limitations hinder optimal performance and generalization in adversarial training.

Purpose of the Study:

To introduce Self-Paced Adversarial Training (SPAT) to improve DNN adversarial robustness.
To address overfitting and catastrophic forgetting in adversarial training.
To provide a quantitative criterion for attack strength and balance adversarial examples across classes.

Main Methods:

SPAT builds the learning process using adversarial examples from the entire dataset.
The model is initially trained with 'easy' adversarial examples, progressively incorporating 'complex' ones.
Adversarial example difficulty is assessed locally within each class to ensure inter-class balance.

Main Results:

SPAT demonstrates effectiveness against diverse attacks on standard benchmarks.
On CIFAR100, SPAT achieved a 1.7% boost in robust accuracy against PGD10 attacks.
SPAT resulted in a 3.9% increase in natural accuracy for Adversarial Weight Perturbation (AWP).

Conclusions:

SPAT offers a novel and effective approach to enhance adversarial robustness in DNNs.
The self-paced learning paradigm successfully mitigates overfitting and catastrophic forgetting.
SPAT can be integrated with other advanced methods to further boost adversarial defense capabilities.