Word-level textual adversarial attacking based on genetic algorithm

Dingmeng Shi; Zhaocheng Ge; Tengfei Zhao

doi:10.1117/12.2659262

28 October 2022 Word-level textual adversarial attacking based on genetic algorithm

Dingmeng Shi, Zhaocheng Ge, Tengfei Zhao

Proceedings Volume 12453, Third International Conference on Computer Communication and Network Security (CCNS 2022); 1245317 (2022) https://doi.org/10.1117/12.2659262
Event: Third International Conference on Computer Communication and Network Security (CCNS 2022), 2022, Hohhot, China

Abstract

Since the discovery of adversarial examples, the research on adversarial examples in the image field has caused an academic boom. In recent years, with the development of artificial intelligence, adversarial samples in the text field have also attracted more and more scholars' research interest. This paper proposes such an adversarial sample generation algorithm in a black box scenario: using a targeted word deletion scoring mechanism, it can find keywords that have a significant impact on the decision of the classifier when the internal structure of the model is unknown, and use the HowNet vocabulary to search the synonyms of these keywords are replaced to generate a set of adversarial samples that are semantically consistent with the original samples. Then combined with genetic algorithm to search for the best sample in the generated sample space. The results of testing LSTM and CNN on sentiment classification and news classification data sets show that the algorithm can greatly reduce the accuracy of the target model with less disturbance.

Citation Download Citation

Dingmeng Shi, Zhaocheng Ge, and Tengfei Zhao "Word-level textual adversarial attacking based on genetic algorithm", Proc. SPIE 12453, Third International Conference on Computer Communication and Network Security (CCNS 2022), 1245317 (28 October 2022); https://doi.org/10.1117/12.2659262

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available