Melola Discovery

← Melola Discovery

Open access Journal SINTA 1

A dilution-based defense method against poisoning attacks on deep learning systems

International Journal of Electrical and Computer Engineering (IJECE) · Vol. 14 No. 1 (2024)

DOI
10.11591/ijece.v14i1.pp645-652
ISSN
2722-2578, 2088-8708
Published
2024-02-01
Publisher
Institute of Advanced Engineering and Science
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Poisoning attack in deep learning (DL) refers to a type of adversarial attack that injects maliciously manipulated data samples into a training dataset for the purpose of forcing a DL model trained based on the poisoned training dataset to misclassify inputs and thus significantly degrading its performance and reliability. Meanwhile, a traditional defense approach against poisoning attacks tries to detect poisoned data samples from the training dataset and then remove them. However, since new sophisticated attacks avoiding existing detection methods continue to emerge, a detection method alone cannot effectively counter poisoning attacks. For this reason, in this paper, we propose a novel dilution-based defense method that mitigates the effect of poisoned data by adding clean data to the training dataset. According to our experiments, our dilution-based defense technique can significantly decrease the success rate of poisoning attacks and improve classification accuracy by effectively reducing the contamination ratio of the manipulated data. Especially, our proposed method outperformed an existing defense method (Cutmix data augmentation) by 20.9%p at most in terms of classification accuracy.

Collaboration network of the authors

3 authors · 2 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Korea National Defense University
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Yeongrok RahKorea National Defense University1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

This record comes from Crossref (what the publisher deposited), because the journal's own OAI-PMH endpoint could not be harvested.

Metadata source: Crossref API (cadangan, berdasarkan ISSN) https://api.crossref.org/journals/2088-8708/works, first harvested 27 Oct 2026, last seen 22 Nov 2026.
Metadata as oai_dc, converted from Crossref
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title>A dilution-based defense method against poisoning attacks on deep learning systems</dc:title><dc:creator>Park, Hweerang</dc:creator><dc:creator>Cho, Youngho</dc:creator><dc:description>&lt;jats:p&gt;Poisoning attack in deep learning (DL) refers to a type of adversarial attack that injects maliciously manipulated data samples into a training dataset for the purpose of forcing a DL model trained based on the poisoned training dataset to misclassify inputs and thus significantly degrading its performance and reliability. Meanwhile, a traditional defense approach against poisoning attacks tries to detect poisoned data samples from the training dataset and then remove them. However, since new sophisticated attacks avoiding existing detection methods continue to emerge, a detection method alone cannot effectively counter poisoning attacks. For this reason, in this paper, we propose a novel dilution-based defense method that mitigates the effect of poisoned data by adding clean data to the training dataset. According to our experiments, our dilution-based defense technique can significantly decrease the success rate of poisoning attacks and improve classification accuracy by effectively reducing the contamination ratio of the manipulated data. Especially, our proposed method outperformed an existing defense method (Cutmix data augmentation) by 20.9%p at most in terms of classification accuracy.&lt;/jats:p&gt;</dc:description><dc:publisher>Institute of Advanced Engineering and Science</dc:publisher><dc:date>2024-02-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/ijece.v14i1.pp645-652</dc:identifier><dc:identifier>10.11591/ijece.v14i1.pp645-652</dc:identifier><dc:source>International Journal of Electrical and Computer Engineering (IJECE); Vol 14 No 1 (2024); 645</dc:source><dc:source>2722-2578</dc:source><dc:source>2088-8708</dc:source><dc:relation>https://ijece.iaescore.com/index.php/IJECE/article/viewFile/32234/17122</dc:relation><dc:rights>http://creativecommons.org/licenses/by-sa/4.0</dc:rights></oai_dc:dc>