Controllable Fake Document Infilling for Cyber Deception

Yibo Hu, Yu Lin, Erick Skorupa Parolin, Latifur Khan, Kevin Hamlen


Abstract
Recent works in cyber deception study how to deter malicious intrusion by generating multiple fake versions of a critical document to impose costs on adversaries who need to identify the correct information. However, existing approaches are context-agnostic, resulting in sub-optimal and unvaried outputs. We propose a novel context-aware model, Fake Document Infilling (FDI), by converting the problem to a controllable mask-then-infill procedure. FDI masks important concepts of varied lengths in the document, then infills a realistic but fake alternative considering both the previous and future contexts. We conduct comprehensive evaluations on technical documents and news stories. Results show that FDI outperforms the baselines in generating highly believable fakes with moderate modification to protect critical information and deceive adversaries.
Anthology ID:
2022.findings-emnlp.486
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6505–6519
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.486
DOI:
10.18653/v1/2022.findings-emnlp.486
Bibkey:
Cite (ACL):
Yibo Hu, Yu Lin, Erick Skorupa Parolin, Latifur Khan, and Kevin Hamlen. 2022. Controllable Fake Document Infilling for Cyber Deception. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6505–6519, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Controllable Fake Document Infilling for Cyber Deception (Hu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.486.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.486.mp4