Diffusion model for adversarial attack against NLP models

Shilin Qiu; Min Gou; Tao Liang

doi:10.1117/12.3026312

27 March 2024 Diffusion model for adversarial attack against NLP models

Shilin Qiu, Min Gou, Tao Liang

Proceedings Volume 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023); 131051T (2024) https://doi.org/10.1117/12.3026312
Event: 3rd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 2023, Qingdao, China

Abstract

Current black-box adversarial attacks have proven to be highly effective in generating adversarial texts that can successfully deceive natural language processing models, thereby revealing potential weaknesses in these models. This research proposes an innovative transfer-based black-box attack method, which capitalizes on the combined generative and discriminative abilities of the diffusion model. To ensure semantic similarity and enhance the adversarial ability of generated texts, well-designed semantic-preserving and adversarial objectives are introduced to the training procedure of the diffusion model. The results show that the proposed method can generate adversarial texts that successfully attack text classification models.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shilin Qiu, Min Gou, and Tao Liang "Diffusion model for adversarial attack against NLP models", Proc. SPIE 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 131051T (27 March 2024); https://doi.org/10.1117/12.3026312

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