• Home
  • Search
  • Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification
  • Cite Icon43
  • https://doi.org/10.1109/icassp40776.2020.9054581Copy DOI Icon

Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification

  • Apr 2, 2020
  • Zhen Xiang +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recently, a special type of data poisoning (DP) attack against deep neural network (DNN) classifiers, known as a backdoor, was proposed. These attacks do not seek to degrade classification accuracy, but rather to have the classifier learn to classify to a target class whenever the backdoor pattern is present in a test example. Here, we address the challenging post-training detection of backdoor attacks in DNN image classifiers, wherein the defender does not have access to the poisoned training set, but only to the trained classifier itself, as well as to clean (unpoisoned) examples from the classification domain. We propose a defense against imperceptible backdoor attacks based on perturbation optimization and novel, robust detection inference. Our method detects whether the trained DNN has been backdoor-attacked and infers the source and target classes involved in an attack. It outperforms alternative defenses for several backdoor patterns, data sets, and attack settings.

Similar Papers
  • Research Article
  • Citations51

Detection of Backdoors in Trained Classifiers Without Access to the Training Set.

  • Dec 16, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Zhen Xiang +2
  • Conference Article

Classification of Bisyllabic Lexical Stress Patterns Using Deep Neural Networks

  • Jan 01, 2016
  • Mostafa Shahin +1
  • Research Article
  • Citations82

Growing random forest on deep convolutional neural networks for scene categorization

  • Oct 17, 2016
  • Expert Systems with Applications
  • Shuang Bai
  • Research Article
  • Citations17

Early detection of infestation by mustard aphid, vegetable thrips and two-spotted spider mite in bok choy with deep neural network (DNN) classification model using hyperspectral imaging data

  • Apr 04, 2024
  • Computers and Electronics in Agriculture
  • Derrick Nguyen Hoang Danh +5
  • Conference Article
  • Citations16

Towards Backdoor Attack on Deep Learning based Time Series Classification

  • May 01, 2022
  • Daizong Ding +6
  • Conference Article
  • Citations2

DNN Classifier and Decision Tree-Based Novel Methodology for Analyzing Road Accidents

  • Sep 01, 2019
  • Shehani N Ariyathilake +1
  • Conference Article
  • Citations10

Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks

  • May 23, 2022
  • Xi Li +3
  • Research Article
  • Citations11

Learning with noisy labels using collaborative sample selection and contrastive semi-supervised learning

  • Apr 27, 2024
  • Knowledge-Based Systems
  • Qing Miao +6
  • Conference Article
  • Citations124

IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

  • May 24, 2021
  • Xiaoyu Cao +2
  • Conference Article
  • Citations45

A Benchmark Study Of Backdoor Data Poisoning Defenses For Deep Neural Network Classifiers And A Novel Defense

  • Oct 01, 2019
  • Zhen Xiang +2
  • Conference Article
  • Citations2

Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes

  • May 24, 2021
  • Jinyuan Jia +2
  • Conference Article
  • Citations8

Deep neural network classifier for hand movement prediction

  • May 01, 2017
  • Alper Basturk +3
  • Research Article

AN ENHANCED METHOD OF LIVER LESION DETECTION USING DEEP NEURAL NETWORK, WATERSHED TRANSFORM AND GAUSSIAN MIXTURE MODEL TECHNIQUES IN MR IMAGES

  • May 23, 2021
  • EPRA International Journal of Research & Development (IJRD)
  • A.Bathshebaparimala +1
  • Conference Article
  • Citations28

Vulnerabilities of Deep Learning-Driven Semantic Communications to Backdoor (Trojan) Attacks

  • Mar 22, 2023
  • Yalin E Sagduyu +3
  • Research Article
  • Citations18

Mapping integrated crop-livestock systems in Brazil with planetscope time series and deep learning

  • Nov 03, 2023
  • Remote Sensing of Environment
  • Inacio T Bueno +9
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.