Masking and purifying inputs for blocking textual adversarial attacks

DOI10.1016/J.INS.2023.119501MaRDI QIDQ6052628zbMATH OpenOpenAlexFDO

Authors

Publication date 22 September 2023

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2023.119501

zbMATH Keywords

adversarial robustnesstextual adversarial attacktextual input refactoringuniversal adversarial defense

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Robustifying models against adversarial attacks by Langevin dynamics
• Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training
• Understanding adversarial robustness via critical attacking route
• A robust generative classifier against transfer attacks based on variational auto-encoders
• Detection of iterative adversarial attacks via counter attack

Cited in

(1)

• Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features

This page was built for publication: Masking and purifying inputs for blocking textual adversarial attacks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6052628)