Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AHZUTKZCW" target="_blank" >RIV/00216208:11320/23:HZUTKZCW - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118115176&doi=10.1109%2fTKDE.2021.3117608&partnerID=40&md5=49d7f261bcfc6933213668123cfc6c27" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118115176&doi=10.1109%2fTKDE.2021.3117608&partnerID=40&md5=49d7f261bcfc6933213668123cfc6c27</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/tkde.2021.3117608" target="_blank" >10.1109/tkde.2021.3117608</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey

Popis výsledku v původním jazyce

"Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are vulnerable to adversarial examples, which cause erroneous predictions by adding imperceptible perturbations into legitimate inputs. Recently, studies have revealed adversarial examples in the text domain, which could effectively evade various DNN-based text analyzers and further bring the threats of the proliferation of disinformation. In this paper, we give a comprehensive survey on the existing studies of adversarial techniques for generating adversarial texts written by both English and Chinese characters and the corresponding defense methods. More importantly, we hope that our work could inspire future studies to develop more robust DNN-based text analyzers against known and unknown adversarial techniques. We classify the existing adversarial techniques for crafting adversarial texts based on the perturbation units, helping to better understand the generation of adversarial texts and build robust models for defense. In presenting the taxonomy of adversarial attacks and defenses in the text domain, we introduce the adversarial techniques from the perspective of different NLP tasks. Finally, we discuss the existing challenges of adversarial attacks and defenses in texts and present the future research directions in this emerging and challenging field. © 1989-2012 IEEE."

Název v anglickém jazyce

Towards a Robust Deep Neural Network Against Adversarial Texts: A Survey

Popis výsledku anglicky

"Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are vulnerable to adversarial examples, which cause erroneous predictions by adding imperceptible perturbations into legitimate inputs. Recently, studies have revealed adversarial examples in the text domain, which could effectively evade various DNN-based text analyzers and further bring the threats of the proliferation of disinformation. In this paper, we give a comprehensive survey on the existing studies of adversarial techniques for generating adversarial texts written by both English and Chinese characters and the corresponding defense methods. More importantly, we hope that our work could inspire future studies to develop more robust DNN-based text analyzers against known and unknown adversarial techniques. We classify the existing adversarial techniques for crafting adversarial texts based on the perturbation units, helping to better understand the generation of adversarial texts and build robust models for defense. In presenting the taxonomy of adversarial attacks and defenses in the text domain, we introduce the adversarial techniques from the perspective of different NLP tasks. Finally, we discuss the existing challenges of adversarial attacks and defenses in texts and present the future research directions in this emerging and challenging field. © 1989-2012 IEEE."

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

"IEEE Transactions on Knowledge and Data Engineering"

ISSN

1041-4347

e-ISSN

—

Svazek periodika

35

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

21

Strana od-do

3159-3179

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85118115176