Towards ABAC Policy Mining from Logs with Deep Learning

Decebal Constantin Mocanu; Fatih Turkmen; Antonio Liotta

Towards ABAC Policy Mining from Logs with Deep Learning

Decebal Constantin Mocanu, Fatih Turkmen, Antonio Liotta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Downloads (Pure)

Abstract

Protection of sensitive information in platforms such as the ones offered by smart cities requires careful enforcement of access control rules that denote " who can/cannot access to what under which circumstances ". In this paper, we propose our ongoing work on the development of a deep learning technique to infer policies from logs. Our proposal improves the state-of-the-art by supporting negative authorizations (i.e. denied access requests) and different types of noise in logs. A preliminary evaluation of the proposed technique is also presented in the paper.

Original language	English
Title of host publication	Proceedings of the 18th International Multiconference - Intelligent Systems, IS 2015
Editors	V.A. Fomichov, O.S. Fomichova
Place of Publication	Ljubljana
Publisher	Jožef Stefan Institute
Publication status	Published - 7 Oct 2015
Event	18th International Multiconference - Intelligent Systems, IS 2015 - Jozef Stefan Institute, Ljubljana, Slovenia Duration: 12 Oct 2015 → 13 Oct 2015 Conference number: 18

Conference

Conference	18th International Multiconference - Intelligent Systems, IS 2015
Abbreviated title	IS
Country	Slovenia
City	Ljubljana
Period	12/10/15 → 13/10/15

Access to Document

Mocanu2015towardsFinal published version, 404 KB

https://research.tue.nl/files/9876041/ABACPolicyMining_author_version.pdf

Fingerprint Dive into the research topics of 'Towards ABAC Policy Mining from Logs with Deep Learning'. Together they form a unique fingerprint.

Cite this

@inproceedings{d4f89dfe2b194fdf93db05666fec92b1,

title = "Towards ABAC Policy Mining from Logs with Deep Learning",

abstract = "Protection of sensitive information in platforms such as the ones offered by smart cities requires careful enforcement of access control rules that denote {"} who can/cannot access to what under which circumstances {"}. In this paper, we propose our ongoing work on the development of a deep learning technique to infer policies from logs. Our proposal improves the state-of-the-art by supporting negative authorizations (i.e. denied access requests) and different types of noise in logs. A preliminary evaluation of the proposed technique is also presented in the paper.",

author = "Mocanu, {Decebal Constantin} and Fatih Turkmen and Antonio Liotta",

year = "2015",

month = oct,

day = "7",

language = "English",

editor = "V.A. Fomichov and O.S. Fomichova",

booktitle = "Proceedings of the 18th International Multiconference - Intelligent Systems, IS 2015",

publisher = "Jo{\v z}ef Stefan Institute",

note = "18th International Multiconference - Intelligent Systems, IS 2015, IS ; Conference date: 12-10-2015 Through 13-10-2015",

}

Mocanu, DC, Turkmen, F & Liotta, A 2015, Towards ABAC Policy Mining from Logs with Deep Learning. in VA Fomichov & OS Fomichova (eds), Proceedings of the 18th International Multiconference - Intelligent Systems, IS 2015. Jožef Stefan Institute, Ljubljana, 18th International Multiconference - Intelligent Systems, IS 2015, Ljubljana, Slovenia, 12/10/15. <https://research.tue.nl/files/9876041/ABACPolicyMining_author_version.pdf>

Towards ABAC Policy Mining from Logs with Deep Learning. / Mocanu, Decebal Constantin; Turkmen, Fatih; Liotta, Antonio.

Proceedings of the 18th International Multiconference - Intelligent Systems, IS 2015. ed. / V.A. Fomichov; O.S. Fomichova. Ljubljana : Jožef Stefan Institute, 2015.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards ABAC Policy Mining from Logs with Deep Learning

AU - Mocanu, Decebal Constantin

AU - Turkmen, Fatih

AU - Liotta, Antonio

N1 - Conference code: 18

PY - 2015/10/7

Y1 - 2015/10/7

N2 - Protection of sensitive information in platforms such as the ones offered by smart cities requires careful enforcement of access control rules that denote " who can/cannot access to what under which circumstances ". In this paper, we propose our ongoing work on the development of a deep learning technique to infer policies from logs. Our proposal improves the state-of-the-art by supporting negative authorizations (i.e. denied access requests) and different types of noise in logs. A preliminary evaluation of the proposed technique is also presented in the paper.

AB - Protection of sensitive information in platforms such as the ones offered by smart cities requires careful enforcement of access control rules that denote " who can/cannot access to what under which circumstances ". In this paper, we propose our ongoing work on the development of a deep learning technique to infer policies from logs. Our proposal improves the state-of-the-art by supporting negative authorizations (i.e. denied access requests) and different types of noise in logs. A preliminary evaluation of the proposed technique is also presented in the paper.

M3 - Conference contribution

BT - Proceedings of the 18th International Multiconference - Intelligent Systems, IS 2015

A2 - Fomichov, V.A.

A2 - Fomichova, O.S.

PB - Jožef Stefan Institute

CY - Ljubljana

T2 - 18th International Multiconference - Intelligent Systems, IS 2015

Y2 - 12 October 2015 through 13 October 2015

ER -