Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation

Hao Tian; Hao-tian Wu; Yiu-ming Cheung; Junhui He; Zhihong Tian

Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation

Hao Tian, Hao-tian Wu^*, Yiu-ming Cheung, Junhui He, Zhihong Tian

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

Original language	English
Title of host publication	Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025
Publisher	IEEE
Publication status	Published - 23 Jun 2025
Event	The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025 - Naples, Italy Duration: 23 Jun 2025 → 26 Jun 2025 https://dsn2025.github.io/cpaccepted.html

Conference

Conference	The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025
Abbreviated title	DSN 2025
Country/Territory	Italy
City	Naples
Period	23/06/25 → 26/06/25
Internet address	https://dsn2025.github.io/cpaccepted.html

Cite this

@inproceedings{cb1e50d3e3b94e439ba1a2d13d7cfa45,

title = "Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation",

author = "Hao Tian and Hao-tian Wu and Yiu-ming Cheung and Junhui He and Zhihong Tian",

year = "2025",

month = jun,

day = "23",

language = "English",

booktitle = "Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025",

publisher = "IEEE",

address = "United States",

note = "The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025, DSN 2025 ; Conference date: 23-06-2025 Through 26-06-2025",

url = "https://dsn2025.github.io/cpaccepted.html",

}

Tian, H, Wu, H, Cheung, Y, He, J & Tian, Z 2025, Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation. in Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025. IEEE, The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025, Naples, Italy, 23/06/25.

Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation. / Tian, Hao; Wu, Hao-tian; Cheung, Yiu-ming et al.
Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025. IEEE, 2025.

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Semantically Improved Adversarial Attack Based on Masked Language Model via Context Preservation

AU - Tian, Hao

AU - Wu, Hao-tian

AU - Cheung, Yiu-ming

AU - He, Junhui

AU - Tian, Zhihong

PY - 2025/6/23

Y1 - 2025/6/23

M3 - Conference proceeding

BT - Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025

PB - IEEE

T2 - The 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, DSN 2025

Y2 - 23 June 2025 through 26 June 2025

ER -