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

Search research articles

Related Experiment Video

Updated: Jan 17, 2026

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights.

Zhengyu Zhao, Hanwei Zhang, Renjue Li

IEEE Transactions on Pattern Analysis and Machine Intelligence

|September 16, 2025

Summary

This summary is machine-generated.

Related Concept Videos

Generalization, Discrimination, and Extinction

Generalization, Discrimination, and Extinction

Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...

You might also read

Related Articles

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

Sort by

Same author

Rapid intraoperative multi-molecular diagnosis of glioma with ultrasound radio frequency signals and deep learning.

EBioMedicine·2023

Same author

The burden of HEV-related acute liver failure in Bangladesh, China and India: a systematic review and meta-analysis.

BMC public health·2023

Same author

Establishment of a predictive nomogram for differentiated thyroid cancer: an inpatient-based retrospective study.

Endokrynologia Polska·2023

Same author

Remnant cholesterol and severity of nonalcoholic fatty liver disease.

Diabetology & metabolic syndrome·2023

Same author

Black phosphorus quantum dots induce myocardial inflammatory responses and metabolic disorders in mice.

Journal of environmental sciences (China)·2023

Same author

15.26Gb/s Si-substrate GaN high-speed visible light photodetector with super-lattice structure.

Optics express·2023

Same journal

A Unified and Fast-Sampling Diffusion Bridge Framework via Stochastic Optimal Control.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Robust 3D Semantic Occupancy Prediction With Calibration-Free Spatial Transformation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Image Restoration via Multi-domain Learning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

This study systematically evaluates transferable adversarial attacks against computer vision defenses. Findings reveal vulnerabilities in state-of-the-art defenses and highlight the need for better evaluation methods for adversarial images.

Area of Science:

Computer Vision
Machine Learning Security
Adversarial Machine Learning

Background:

Transferable adversarial images pose significant security risks to computer vision systems in real-world black-box scenarios.
Existing evaluations of transfer attacks lack systematic analysis and comprehensive assessment.

Purpose of the Study:

To systematically categorize and comprehensively evaluate transfer attacks against various defenses.
To identify and address limitations in current evaluation methodologies for attack transferability and stealthiness.

Main Methods:

Systematized 23 representative transfer attacks into five categories within the machine learning pipeline.
Evaluated attacks against 11 representative defenses, including recent transfer-oriented and real-world defenses like Google Cloud Vision.

Related Experiment Videos

Last Updated: Jan 17, 2026

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping

Published on: December 8, 2023

Analyzed attack transferability with fair hyperparameter settings and assessed stealthiness using diverse metrics and a user study.

Main Results:

Identified critical issues in existing evaluations leading to misleading conclusions.
Discovered that an early attack (DI) outperforms later ones, and state-of-the-art defenses (e.g., DiffPure) are vulnerable to black-box transfer attacks.
Demonstrated significant variations in attack stealthiness under the same Lp constraint, based on diverse imperceptibility metrics and user perception.

Conclusions:

Current evaluation practices for transferable adversarial images are flawed, necessitating revised methodologies.
Addressing evaluation shortcomings reveals new insights into attack effectiveness and defense vulnerabilities.
The study provides guidance for improved evaluation of adversarial images, advancing the design of more robust attacks and defenses.