• Home
  • Search
  • Label-Free Poisoning Attack Against Deep Unsupervised Domain Adaptation
  • Cite Icon5
  • https://doi.org/10.1109/tdsc.2023.3286608Copy DOI Icon

Label-Free Poisoning Attack Against Deep Unsupervised Domain Adaptation

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Deep unsupervised domain adaptation (UDA) has significantly boosted the performance of deep models on different domains by transferring knowledge from a source domain to a target domain. However, its robustness against adversarial attacks has not been explored due to the challenges of highly non-convex deep models and different data distribution. In this paper, we give the first attempt to analyze the vulnerability of deep UDA and propose a label-free poisoning attack (LFPA), which injects poisoning data into the training data to mislead adaptation between the two domains without ground truth in target domain. Specifically, we design an unsupervised adversarial loss as the attack goal, in which the pseudo-labels are used to approximate the ground-truth. Since retraining the model will gradually degrade the attack performance, we also add a regularization term to the unsupervised loss, which eliminates negative interactions between the training goal and the attack goal. To accelerate the craft of poisons, we select influential samples as the initial poisons and propose a fast reverse-mode optimization method which updates poisons according to the approximate truncated gradients. Experimental results on multiple state-of-the-art deep UDA methods demonstrate the effectiveness of the proposed LFPA and the high sensitivity of UDA to poisoning attacks.

Similar Papers
  • Book Chapter
  • Citations106

Data Efficient Unsupervised Domain Adaptation For Cross-modality Image Segmentation

  • Jan 01, 2019
  • Cheng Ouyang +4
  • Research Article
  • Citations13

Transfer channel pruning for compressing deep domain adaptation models

  • Sep 11, 2019
  • International Journal of Machine Learning and Cybernetics
  • Chaohui Yu +3
  • Research Article
  • Citations277

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

  • Aug 16, 2022
  • APSIPA Transactions on Signal and Information Processing
  • Xiaofeng Liu +6
  • Research Article

Deep Unsupervised Domain Adaptation for Translating Cancer Dependency Maps From Cell Lines to Breast Cancer Tumor Genomics.

  • Jul 01, 2026
  • Genetic epidemiology
  • Yu Shi +2
  • Book Chapter
  • Citations38

MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels

  • Jan 01, 2021
  • Ziyuan Zhao +4
  • Book Chapter
  • Citations5

Transfer Channel Pruning for Compressing Deep Domain Adaptation Models

  • Jan 01, 2019
  • Chaohui Yu +3
  • Research Article

DUDE: deep unsupervised domain adaptation using variable nEighbors for physiological time series analysis

  • Dec 30, 2025
  • Physiological Measurement
  • Jeremy Levy +3
  • Conference Article
  • Citations24

Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning

  • Jul 01, 2019
  • Chaohui Yu +3
  • PDF
  • Supplementary Content
  • Citations68

Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey

  • Jul 23, 2022
  • Sensors (Basel, Switzerland)
  • Yongjie Shi +2
  • Abstract

Unsupervised Domain Adaptation of Auto-Segmentation on Multi-Source MRIs

  • Sep 29, 2023
  • International Journal of Radiation Oncology*Biology*Physics
  • W Zhang +4
  • Research Article
  • Citations15

Unsupervised Multitarget Domain Adaptation With Dictionary-Bridged Knowledge Exploitation.

  • Mar 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qing Tian +5
  • Research Article
  • Citations121

Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks.

  • Nov 01, 2022
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jingjing Li +5
  • Book Chapter
  • Citations2

DUDA: Deep Unsupervised Domain Adaptation Learning for Multi-sequence Cardiac MR Image Segmentation

  • Jan 01, 2020
  • Yueguo Liu +1
  • Research Article
  • Citations351

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation.

  • Feb 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Sicheng Zhao +10
  • Conference Article
  • Citations10

Class Consistency Driven Unsupervised Deep Adversarial Domain Adaptation

  • Jun 01, 2019
  • Sayan Rakshit +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.