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

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...

Feedback control systems

Feedback control systems

Feedback control systems are categorized in various ways based on their design, analysis, and signal types.
Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

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...

You might also read

Related Articles

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

Sort by

Same author

Single-point insulin sensitivity estimator and atrial fibrillation: association and incremental discriminative value in a hospital-based population.

Frontiers in endocrinology·2026

Same author

Dual-functional monomers synergistically facilitate the assembly of a CoNiZn@C-based molecularly imprinted electrochemical sensor for highly sensitive detection of zearalenone.

Mikrochimica acta·2026

Same author

Association of the single-point insulin sensitivity estimator with arterial stiffness: a cross-sectional analysis.

Frontiers in endocrinology·2026

Same author

Interactive multimodal disease risk evaluation using a self-service non-invasive device.

Communications medicine·2026

Same author

Effects of spray-freeze-dried microcapsules with different proportions of hydroxypropyl methylcellulose and whey protein isolate on the viability and release property of probiotics.

Food chemistry·2026

Same author

Seeking Flat Minima Over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation.

IEEE transactions on pattern analysis and machine intelligence·2026

Search research articles

Related Experiment Video

Updated: Jul 2, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

Defenses in Adversarial Machine Learning: A Systematic Survey From the Lifecycle Perspective.

Baoyuan Wu, Mingli Zhu, Meixi Zheng

IEEE Transactions on Pattern Analysis and Machine Intelligence

|September 17, 2025

Summary

Machine learning (ML) systems face security threats from adversarial attacks. This survey unifies defense strategies across the ML lifecycle, offering a new perspective for robust model development.

More Related Videos

High-Throughput Behavioral Aging and Lifespan Assays Using the Lifespan Machine

High-Throughput Behavioral Aging and Lifespan Assays Using the Lifespan Machine

Published on: January 26, 2024

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

Related Experiment Videos

Last Updated: Jul 2, 2026

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

High-Throughput Behavioral Aging and Lifespan Assays Using the Lifespan Machine

High-Throughput Behavioral Aging and Lifespan Assays Using the Lifespan Machine

Published on: January 26, 2024

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

A Real-Time Interactive System for Studying Confrontational Pursuit Behavior in Rodents

Published on: May 16, 2025

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning Security

Background:

Machine learning (ML) systems, particularly deep neural networks, exhibit adversarial phenomena, producing inconsistent and incomprehensible predictions.
These vulnerabilities pose significant security risks, leading to the development of attack paradigms like backdoor attacks, weight attacks, and adversarial examples.
Existing defense mechanisms are often specific to individual attack types, making overall system robustness assessment challenging.

Purpose of the Study:

To systematically review existing defense paradigms against adversarial attacks in ML systems.
To provide a unified lifecycle perspective for analyzing and categorizing defense methods.
To foster the development of more comprehensive and advanced defense strategies.

Main Methods:

Decomposition of ML systems into five lifecycle stages: pre-training, training, post-training, deployment, and inference.
Development of a clear taxonomy to categorize representative defense methods within each stage.
Analysis of defense mechanisms from a unified lifecycle viewpoint.

Main Results:

A systematic review and categorization of defense methods against ML adversarial attacks.
A unified lifecycle perspective that clarifies connections and differences among various defense paradigms.
Identification of research gaps and inspiration for future comprehensive defense strategies.

Conclusions:

A unified lifecycle approach is crucial for understanding and developing robust defenses against diverse adversarial attacks in ML.
The proposed taxonomy aids in analyzing existing defenses and guides future research towards more integrated solutions.
This work provides a foundational framework for enhancing the security and reliability of ML systems.