Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach

Mohammadreza Ebrahimi; Sagar Samtani; Yidong Chai; Hsinchun Chen

doi:10.1109/SPW50608.2020.00021

Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach

Mohammadreza Ebrahimi
, Sagar Samtani
, Yidong Chai^*
, Hsinchun Chen

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

16 Citations (Scopus)

Abstract

The regularity of devastating cyber-attacks has made cybersecurity a grand societal challenge. Many cybersecurity professionals are closely examining the international Dark Web to proactively pinpoint potential cyber threats. Despite its potential, the Dark Web contains hundreds of thousands of non-English posts. While machine translation is the prevailing approach to process non-English text, applying MT on hacker forum text results in mistranslations. In this study, we draw upon Long-Short Term Memory (LSTM), Cross-Lingual Knowledge Transfer (CLKT), and Generative Adversarial Networks (GANs) principles to design a novel Adversarial CLKT (A-CLKT) approach. A-CLKT operates on untranslated text to retain the original semantics of the language and leverages the collective knowledge about cyber threats across languages to create a language invariant representation without any manual feature engineering or external resources. Three experiments demonstrate how A-CLKT outperforms state-of-the-art machine learning, deep learning, and CLKT algorithms in identifying cyber-threats in French and Russian forums.

© 2020, Mohammadreza Ebrahimi. Under license to IEEE.

Original language	English
Title of host publication	Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020)
Publisher	IEEE
Pages	20-26
Number of pages	7
ISBN (Electronic)	978-1-7281-9346-5
DOIs	https://doi.org/10.1109/SPW50608.2020.00021
Publication status	Published - 2020
Externally published	Yes
Event	2020 IEEE Symposium on Security and Privacy Workshops, SPW 2020 - Virtual, San Francisco, United States Duration: 21 May 2020 → …

Publication series

Name	Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW

Conference

Conference	2020 IEEE Symposium on Security and Privacy Workshops, SPW 2020
Place	United States
City	Virtual, San Francisco
Period	21/05/20 → …

Funding

This material is based upon work supported by the National Science Foundation (NSF) under Grants SES-1314631 (SaTC SBE), ACI-1443019 (DIBBs), CNS-1936370 (SaTC CORE), and CNS-1850362 (CRII SaTC).

Research Keywords

Adversarial learning
Cross-lingual knowledge transfer
Generative adversarial networks
Hacker forums
Long short-term memory

Access Output

10.1109/SPW50608.2020.00021

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Ebrahimi, M., Samtani, S., Chai, Y., & Chen, H. (2020). Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach. In Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020) (pp. 20-26). Article 9283883 (Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW). IEEE. https://doi.org/10.1109/SPW50608.2020.00021

@inproceedings{ab4d95bc70b54272b97c198e844fe06b,

title = "Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach",

abstract = "The regularity of devastating cyber-attacks has made cybersecurity a grand societal challenge. Many cybersecurity professionals are closely examining the international Dark Web to proactively pinpoint potential cyber threats. Despite its potential, the Dark Web contains hundreds of thousands of non-English posts. While machine translation is the prevailing approach to process non-English text, applying MT on hacker forum text results in mistranslations. In this study, we draw upon Long-Short Term Memory (LSTM), Cross-Lingual Knowledge Transfer (CLKT), and Generative Adversarial Networks (GANs) principles to design a novel Adversarial CLKT (A-CLKT) approach. A-CLKT operates on untranslated text to retain the original semantics of the language and leverages the collective knowledge about cyber threats across languages to create a language invariant representation without any manual feature engineering or external resources. Three experiments demonstrate how A-CLKT outperforms state-of-the-art machine learning, deep learning, and CLKT algorithms in identifying cyber-threats in French and Russian forums. {\textcopyright} 2020, Mohammadreza Ebrahimi. Under license to IEEE.",

keywords = "Adversarial learning, Cross-lingual knowledge transfer, Generative adversarial networks, Hacker forums, Long short-term memory",

author = "Mohammadreza Ebrahimi and Sagar Samtani and Yidong Chai and Hsinchun Chen",

year = "2020",

doi = "10.1109/SPW50608.2020.00021",

language = "English",

series = "Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW",

publisher = "IEEE",

pages = "20--26",

booktitle = "Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020)",

address = "United States",

note = "2020 IEEE Symposium on Security and Privacy Workshops, SPW 2020 ; Conference date: 21-05-2020",

}

Ebrahimi, M, Samtani, S, Chai, Y & Chen, H 2020, Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach. in Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020)., 9283883, Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW, IEEE, pp. 20-26, 2020 IEEE Symposium on Security and Privacy Workshops, SPW 2020, Virtual, San Francisco, United States, 21/05/20. https://doi.org/10.1109/SPW50608.2020.00021

Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach. / Ebrahimi, Mohammadreza; Samtani, Sagar; Chai, Yidong et al.
Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020). IEEE, 2020. p. 20-26 9283883 (Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Detecting cyber threats in non-english hacker forums

T2 - 2020 IEEE Symposium on Security and Privacy Workshops, SPW 2020

AU - Ebrahimi, Mohammadreza

AU - Samtani, Sagar

AU - Chai, Yidong

AU - Chen, Hsinchun

PY - 2020

Y1 - 2020

N2 - The regularity of devastating cyber-attacks has made cybersecurity a grand societal challenge. Many cybersecurity professionals are closely examining the international Dark Web to proactively pinpoint potential cyber threats. Despite its potential, the Dark Web contains hundreds of thousands of non-English posts. While machine translation is the prevailing approach to process non-English text, applying MT on hacker forum text results in mistranslations. In this study, we draw upon Long-Short Term Memory (LSTM), Cross-Lingual Knowledge Transfer (CLKT), and Generative Adversarial Networks (GANs) principles to design a novel Adversarial CLKT (A-CLKT) approach. A-CLKT operates on untranslated text to retain the original semantics of the language and leverages the collective knowledge about cyber threats across languages to create a language invariant representation without any manual feature engineering or external resources. Three experiments demonstrate how A-CLKT outperforms state-of-the-art machine learning, deep learning, and CLKT algorithms in identifying cyber-threats in French and Russian forums. © 2020, Mohammadreza Ebrahimi. Under license to IEEE.

AB - The regularity of devastating cyber-attacks has made cybersecurity a grand societal challenge. Many cybersecurity professionals are closely examining the international Dark Web to proactively pinpoint potential cyber threats. Despite its potential, the Dark Web contains hundreds of thousands of non-English posts. While machine translation is the prevailing approach to process non-English text, applying MT on hacker forum text results in mistranslations. In this study, we draw upon Long-Short Term Memory (LSTM), Cross-Lingual Knowledge Transfer (CLKT), and Generative Adversarial Networks (GANs) principles to design a novel Adversarial CLKT (A-CLKT) approach. A-CLKT operates on untranslated text to retain the original semantics of the language and leverages the collective knowledge about cyber threats across languages to create a language invariant representation without any manual feature engineering or external resources. Three experiments demonstrate how A-CLKT outperforms state-of-the-art machine learning, deep learning, and CLKT algorithms in identifying cyber-threats in French and Russian forums. © 2020, Mohammadreza Ebrahimi. Under license to IEEE.

KW - Adversarial learning

KW - Cross-lingual knowledge transfer

KW - Generative adversarial networks

KW - Hacker forums

KW - Long short-term memory

UR - https://www.scopus.com/pages/publications/85099724665

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85099724665&origin=recordpage

U2 - 10.1109/SPW50608.2020.00021

DO - 10.1109/SPW50608.2020.00021

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW

SP - 20

EP - 26

BT - Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020)

PB - IEEE

Y2 - 21 May 2020

ER -

Ebrahimi M, Samtani S, Chai Y, Chen H. Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach. In Proceedings - 2020 IEEE Symposium on Security and Privacy Workshops (SPW 2020). IEEE. 2020. p. 20-26. 9283883. (Proceedings - IEEE Symposium on Security and Privacy Workshops, SPW). Epub 2020 Dec 18. doi: 10.1109/SPW50608.2020.00021

Detecting cyber threats in non-english hacker forums: An adversarial cross-lingual knowledge transfer approach

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this