Passtrans: An Improved Password Reuse Model Based on Transformer

Xiaoxi  He; Haibo  Cheng; Jiahong  Xie; Ping Wang; Kaitai Liang

doi:10.1109/ICASSP43922.2022.9746731

Passtrans: An Improved Password Reuse Model Based on Transformer

Xiaoxi He, Haibo Cheng^*, Jiahong Xie, Ping Wang^*, Kaitai Liang

^*Corresponding author for this work

Cyber Security

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

1 Citation (Scopus)

43 Downloads (Pure)

Abstract

Passwords have been widely used in online authentication, and they form the front line that protects our data security and privacy. But the security of password may be easily harmed by insecure password generator. Massive reports state that users are always keen to generate new passwords by reusing or fine-tuning old secrets. Once an old password is leaked, the users may suffer from credential tweaking attacks. We propose a password reuse model PassTrans and simulate credential tweaking attacks. We evaluate the performance in leaked password datasets, and the results show that 67.51% of accounts is breakable under 1,000 guesses, indicating our model is accurate in capturing password reuse behavior.

Original language	English
Title of host publication	Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of Publication	Piscataway
Publisher	IEEE
Pages	3044-3048
Number of pages	5
ISBN (Electronic)	978-1-6654-0540-9
ISBN (Print)	978-1-6654-0541-6
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746731
Publication status	Published - 2022
Event	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Singapore, Singapore Duration: 23 May 2022 → 27 May 2022

Conference

Conference	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Country/Territory	Singapore
City	Singapore
Period	23/05/22 → 27/05/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

credential tweaking attack
password model
password reuse
similarity

Access to Document

10.1109/ICASSP43922.2022.9746731

Passtrans_An_Improved_Password_Reuse_Model_Based_on_TransformerFinal published version, 1.97 MB

Cite this

@inproceedings{e5432579616c47b7be8d3fa4abdc70fc,

title = "Passtrans: An Improved Password Reuse Model Based on Transformer",

abstract = "Passwords have been widely used in online authentication, and they form the front line that protects our data security and privacy. But the security of password may be easily harmed by insecure password generator. Massive reports state that users are always keen to generate new passwords by reusing or fine-tuning old secrets. Once an old password is leaked, the users may suffer from credential tweaking attacks. We propose a password reuse model PassTrans and simulate credential tweaking attacks. We evaluate the performance in leaked password datasets, and the results show that 67.51% of accounts is breakable under 1,000 guesses, indicating our model is accurate in capturing password reuse behavior.",

keywords = "credential tweaking attack, password model, password reuse, similarity",

author = "Xiaoxi He and Haibo Cheng and Jiahong Xie and Ping Wang and Kaitai Liang",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746731",

language = "English",

isbn = "978-1-6654-0541-6",

pages = "3044--3048",

booktitle = "Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "IEEE",

address = "United States",

}

He, X, Cheng, H, Xie, J, Wang, P & Liang, K 2022, Passtrans: An Improved Password Reuse Model Based on Transformer. in Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 9746731, IEEE, Piscataway, pp. 3044-3048, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 23/05/22. https://doi.org/10.1109/ICASSP43922.2022.9746731

Passtrans: An Improved Password Reuse Model Based on Transformer. / He, Xiaoxi ; Cheng, Haibo ; Xie, Jiahong et al.
Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE, 2022. p. 3044-3048 9746731.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Passtrans

T2 - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

AU - He, Xiaoxi

AU - Cheng, Haibo

AU - Xie, Jiahong

AU - Wang, Ping

AU - Liang, Kaitai

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - Passwords have been widely used in online authentication, and they form the front line that protects our data security and privacy. But the security of password may be easily harmed by insecure password generator. Massive reports state that users are always keen to generate new passwords by reusing or fine-tuning old secrets. Once an old password is leaked, the users may suffer from credential tweaking attacks. We propose a password reuse model PassTrans and simulate credential tweaking attacks. We evaluate the performance in leaked password datasets, and the results show that 67.51% of accounts is breakable under 1,000 guesses, indicating our model is accurate in capturing password reuse behavior.

AB - Passwords have been widely used in online authentication, and they form the front line that protects our data security and privacy. But the security of password may be easily harmed by insecure password generator. Massive reports state that users are always keen to generate new passwords by reusing or fine-tuning old secrets. Once an old password is leaked, the users may suffer from credential tweaking attacks. We propose a password reuse model PassTrans and simulate credential tweaking attacks. We evaluate the performance in leaked password datasets, and the results show that 67.51% of accounts is breakable under 1,000 guesses, indicating our model is accurate in capturing password reuse behavior.

KW - credential tweaking attack

KW - password model

KW - password reuse

KW - similarity

UR - http://www.scopus.com/inward/record.url?scp=85131234963&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746731

DO - 10.1109/ICASSP43922.2022.9746731

M3 - Conference contribution

SN - 978-1-6654-0541-6

SP - 3044

EP - 3048

BT - Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

CY - Piscataway

Y2 - 23 May 2022 through 27 May 2022

ER -

Passtrans: An Improved Password Reuse Model Based on Transformer

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this