Jove
Visualize
Contact Us

Related Concept Videos

Nonconscious Mimicry01:13

Nonconscious Mimicry

5.0K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
5.0K
Understanding Deception01:14

Understanding Deception

119
Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...
119
Masking and Demasking Agents01:19

Masking and Demasking Agents

3.3K
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...
3.3K
Predator-Prey Interactions02:39

Predator-Prey Interactions

20.9K
Predators consume prey for energy. Predators that acquire prey and prey that avoid predation both increase their chances of survival and reproduction (i.e., fitness). Routine predator-prey interactions elicit mutual adaptations that improve predator offenses, such as claws, teeth, and speed, as well as prey defenses, including crypsis, aposematism, and mimicry. Thus, predator-prey interactions resemble an evolutionary arms race.
20.9K
Stereotype Content Model02:16

Stereotype Content Model

15.2K
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...
15.2K
Agonism and Antagonism: Quantification01:14

Agonism and Antagonism: Quantification

875
When drugs are administered, they can elicit either an agonist or antagonist effect on the body. Agonism occurs when a drug activates a specific receptor, triggering a biological response. On the other hand, antagonism happens when a drug binds to the same receptors but blocks their activation, thereby preventing a biological response.
To quantify these effects, researchers use a dose-response curve, which provides valuable information about the potency and efficacy of a drug. Potency refers to...
875

You might also read

Related Articles

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

Sort by
Same author

Benchmarking deep learning models for predicting anticancer drug potency (IC<sub>50</sub>) with insights for medicinal chemists.

Communications chemistry·2026
Same author

A deep learning framework for species-level identification of root-knot nematodes using perineal pattern images.

Scientific reports·2026
Same author

SEMI-CAVA: A Causal Variational Approach to Semi-Supervised Learning.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

MedTric : A clinically applicable metric for evaluation of multi-label computational diagnostic systems.

PloS one·2023
Same author

MICaps: Multi-instance capsule network for machine inspection of Munro's microabscess.

Computers in biology and medicine·2021
Same author

Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network.

Computer methods and programs in biomedicine·2018
Same journal

Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

IEEE transactions on neural networks and learning systems·2026
Same journal

Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

IEEE transactions on neural networks and learning systems·2026
Same journal

HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

IEEE transactions on neural networks and learning systems·2026
Same journal

Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

IEEE transactions on neural networks and learning systems·2026
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Dec 23, 2025

Establishment of a Valuable Mimic of Alzheimer's Disease in Rat Animal Model by Intracerebroventricular Injection of Composited Amyloid Beta Protein
08:27

Establishment of a Valuable Mimic of Alzheimer's Disease in Rat Animal Model by Intracerebroventricular Injection of Composited Amyloid Beta Protein

Published on: July 29, 2018

12.4K

Mimic and Fool: A Task-Agnostic Adversarial Attack.

Akshay Chaturvedi, Utpal Garain

    IEEE Transactions on Neural Networks and Learning Systems
    |April 21, 2020
    PubMed
    Summary
    This summary is machine-generated.

    We introduce Mimic and Fool (MaF), a novel task-agnostic adversarial attack for computer vision. This method generates adversarial images that fool deep learning models across various downstream tasks by mimicking essential image features.

    Related Experiment Videos

    Last Updated: Dec 23, 2025

    Establishment of a Valuable Mimic of Alzheimer's Disease in Rat Animal Model by Intracerebroventricular Injection of Composited Amyloid Beta Protein
    08:27

    Establishment of a Valuable Mimic of Alzheimer's Disease in Rat Animal Model by Intracerebroventricular Injection of Composited Amyloid Beta Protein

    Published on: July 29, 2018

    12.4K

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Adversarial Machine Learning

    Background:

    • Current adversarial attacks are task-specific, limiting their broad applicability.
    • Deep learning models in computer vision often use shared feature extractors (e.g., VGG16, ResNet50) for diverse tasks like image captioning and segmentation.

    Purpose of the Study:

    • To develop a task-agnostic adversarial attack that can fool models regardless of the specific downstream application.
    • To create adversarial images that mimic the feature representations of original images, ensuring similar outputs across tasks.

    Main Methods:

    • Proposed Mimic and Fool (MaF) attack, a gray-box method requiring only feature extractor information.
    • Experimented on 1000 MSCOCO validation images using image captioning (Show and Tell, Show Attend and Tell) and visual question answering (N2NMN) models.
    • Introduced a modification for generating natural-looking adversarial images and demonstrated applicability for invertible architectures.

    Main Results:

    • Achieved high success rates: 74.0% for Show and Tell, 81.0% for Show Attend and Tell, and 87.1% for N2NMN.
    • Demonstrated the effectiveness of MaF in fooling models across different computer vision tasks.
    • Successfully generated natural-looking adversarial images and showed applicability to invertible architectures.

    Conclusions:

    • MaF offers a versatile and effective task-agnostic adversarial attack for computer vision systems.
    • The attack's gray-box nature and ability to mimic features make it a significant advancement in adversarial robustness research.
    • Future work can explore further refinements for naturalness and broader applicability in diverse deep learning architectures.