• Home
  • Search
  • Enhancing Generalization in Few-Shot Learning for Detecting Unknown Adversarial Examples
  • Cite Icon4
  • https://doi.org/10.1007/s11063-024-11572-6Copy DOI Icon

Enhancing Generalization in Few-Shot Learning for Detecting Unknown Adversarial Examples

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep neural networks, particularly convolutional neural networks, are vulnerable to adversarial examples, undermining their reliability in visual recognition tasks. Adversarial example detection is a crucial defense mechanism against such attacks but often relies on empirical observations and specialized metrics, posing challenges in terms of data efficiency, generalization to unknown attacks, and scalability to high-resolution datasets like ImageNet. To address these issues, we propose a prototypical network-based method using a deep residual network as the backbone architecture. This approach is capable of extracting discriminative features of adversarial and normal examples from various known adversarial examples by constructing few-shot adversarial detection tasks. Then the optimal mapping matrix is computed using the Sinkhorn algorithm from optimal transport theory, and the class centers are iteratively updated, enabling the detection of unknown adversarial examples across scenarios. Experimental results show that the proposed approach outperforms existing methods in the cross-adversary benchmark and achieves enhanced generalization on a subset of ImageNet in detecting both new adversarial attacks and adaptive white-box attacks. The proposed approach offers a promising solution for improving the safety of deep neural networks in practical applications.

Loading PDF

Similar Papers
  • Research Article
  • Citations2

Restoration of Adversarial Examples Using Image Arithmetic Operations

  • Jan 01, 2022
  • Intelligent Automation & Soft Computing
  • Kazim Ali +1
  • Research Article
  • Citations1

Generating watermarked adversarial texts

  • Mar 28, 2023
  • Journal of Electronic Imaging
  • Mingjie Li +3
  • Research Article
  • Citations20

Toward Transferable Attack via Adversarial Diffusion in Face Recognition

  • Jan 01, 2024
  • IEEE Transactions on Information Forensics and Security
  • Cong Hu +3
  • PDF
  • Research Article
  • Citations2

PSI Analysis of Adversarial-Attacked DCNN Models

  • Aug 28, 2023
  • Applied Sciences
  • Youngseok Lee +1
  • Research Article
  • Citations90

Analyzing the Noise Robustness of Deep Neural Networks.

  • Jan 23, 2020
  • IEEE Transactions on Visualization and Computer Graphics
  • Kelei Cao +5
  • Conference Article
  • Citations56

Analyzing the Noise Robustness of Deep Neural Networks

  • Oct 01, 2018
  • Mengchen Liu +4
  • Book Chapter
  • Citations22

Adversarial Examples in Deep Neural Networks: An Overview

  • Oct 24, 2019
  • Emilio Rafael Balda +2
  • Research Article
  • Citations1

Generating traceable adversarial text examples by watermarking in the semantic space

  • Nov 26, 2022
  • Journal of Electronic Imaging
  • Mingjie Li +2
  • Research Article
  • Citations7

Improving the Transferability of Adversarial Attacks on Face Recognition With Beneficial Perturbation Feature Augmentation

  • Dec 01, 2024
  • IEEE Transactions on Computational Social Systems
  • Fengfan Zhou +5
  • Research Article

A spatial-frequency domain joint detection method of adversarial examples for signal modulation recognition network

  • Mar 23, 2026
  • Cybersecurity
  • Wenlin Liu +5
  • Conference Article
  • Citations10

Fooling a Neural Network in Military Environments: Random Untargeted Adversarial Example

  • Oct 01, 2018
  • Hyun Kwon +3
  • Conference Article

Adversarial example generation using object detection

  • Oct 19, 2022
  • Liang Gu +6
  • Research Article
  • Citations3

FCDM: A Methodology Based on Sensor Pattern Noise Fingerprinting for Fast Confidence Detection to Adversarial Attacks

  • Jan 31, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Yazhu Lan +6
  • Research Article
  • Citations49

Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Voting.

  • Mar 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Federico Nesti +2
  • Conference Article
  • Citations58

Adversarial Examples in Deep Learning for Multivariate Time Series Regression

  • Oct 13, 2020
  • Gautam Raj Mode +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.