Poster: Effective layers in coverage metrics for deep neural networks

Leo Hyun Park; Sangjin Oh; Jaeuk Kim; Soochang Chung; Taekyoung Kwon

doi:10.1145/3319535.3363286

Poster: Effective layers in coverage metrics for deep neural networks

Leo Hyun Park, Sangjin Oh, Jaeuk Kim, Soochang Chung, Taekyoung Kwon

Graduate School of Information

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Deep neural networks (DNNs) gained in popularity as an effective machine learning algorithm, but their high complexity leads to the lack of model interpretability and difficulty in the verification of deep learning. Fuzzing, which is an automated software testing technique, is recently applied to DNNs as an effort to address these problems by following the trend of coverage-based fuzzing. However, new coverage metrics on DNNs may bring out the question of which layer to measure the coverage in DNNs. In this poster, we empirically evaluate the performance of existing coverage metrics. By the comparative analysis of experimental results, we compile the most effective layer for each of coverage metrics and discuss a future direction of DNN fuzzing.

Original language	English
Title of host publication	CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security
Publisher	Association for Computing Machinery
Pages	2681-2683
Number of pages	3
ISBN (Electronic)	9781450367479
DOIs	https://doi.org/10.1145/3319535.3363286
Publication status	Published - 2019 Nov 6
Event	26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019 - London, United Kingdom Duration: 2019 Nov 11 → 2019 Nov 15

Publication series

Name	Proceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)	1543-7221

Conference

Conference	26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019
Country/Territory	United Kingdom
City	London
Period	19/11/11 → 19/11/15

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1A2C1088802).

Publisher Copyright:
© 2019 Association for Computing Machinery.

All Science Journal Classification (ASJC) codes

Software
Computer Networks and Communications

Access to Document

10.1145/3319535.3363286

Cite this

Park, L. H., Oh, S., Kim, J., Chung, S., & Kwon, T. (2019). Poster: Effective layers in coverage metrics for deep neural networks. In CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (pp. 2681-2683). (Proceedings of the ACM Conference on Computer and Communications Security). Association for Computing Machinery. https://doi.org/10.1145/3319535.3363286

@inproceedings{a305011308f840d0a9fd2497bbfd17bd,

title = "Poster: Effective layers in coverage metrics for deep neural networks",

abstract = "Deep neural networks (DNNs) gained in popularity as an effective machine learning algorithm, but their high complexity leads to the lack of model interpretability and difficulty in the verification of deep learning. Fuzzing, which is an automated software testing technique, is recently applied to DNNs as an effort to address these problems by following the trend of coverage-based fuzzing. However, new coverage metrics on DNNs may bring out the question of which layer to measure the coverage in DNNs. In this poster, we empirically evaluate the performance of existing coverage metrics. By the comparative analysis of experimental results, we compile the most effective layer for each of coverage metrics and discuss a future direction of DNN fuzzing.",

author = "Park, {Leo Hyun} and Sangjin Oh and Jaeuk Kim and Soochang Chung and Taekyoung Kwon",

note = "Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1A2C1088802). Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019 ; Conference date: 11-11-2019 Through 15-11-2019",

year = "2019",

month = nov,

day = "6",

doi = "10.1145/3319535.3363286",

language = "English",

series = "Proceedings of the ACM Conference on Computer and Communications Security",

publisher = "Association for Computing Machinery",

pages = "2681--2683",

booktitle = "CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security",

}

Park, LH, Oh, S, Kim, J, Chung, S & Kwon, T 2019, Poster: Effective layers in coverage metrics for deep neural networks. in CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security. Proceedings of the ACM Conference on Computer and Communications Security, Association for Computing Machinery, pp. 2681-2683, 26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019, London, United Kingdom, 19/11/11. https://doi.org/10.1145/3319535.3363286

Poster : Effective layers in coverage metrics for deep neural networks. / Park, Leo Hyun; Oh, Sangjin; Kim, Jaeuk et al.

CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery, 2019. p. 2681-2683 (Proceedings of the ACM Conference on Computer and Communications Security).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Poster

T2 - 26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019

AU - Park, Leo Hyun

AU - Oh, Sangjin

AU - Kim, Jaeuk

AU - Chung, Soochang

AU - Kwon, Taekyoung

N1 - Funding Information: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1A2C1088802). Publisher Copyright: © 2019 Association for Computing Machinery.

PY - 2019/11/6

Y1 - 2019/11/6

N2 - Deep neural networks (DNNs) gained in popularity as an effective machine learning algorithm, but their high complexity leads to the lack of model interpretability and difficulty in the verification of deep learning. Fuzzing, which is an automated software testing technique, is recently applied to DNNs as an effort to address these problems by following the trend of coverage-based fuzzing. However, new coverage metrics on DNNs may bring out the question of which layer to measure the coverage in DNNs. In this poster, we empirically evaluate the performance of existing coverage metrics. By the comparative analysis of experimental results, we compile the most effective layer for each of coverage metrics and discuss a future direction of DNN fuzzing.

AB - Deep neural networks (DNNs) gained in popularity as an effective machine learning algorithm, but their high complexity leads to the lack of model interpretability and difficulty in the verification of deep learning. Fuzzing, which is an automated software testing technique, is recently applied to DNNs as an effort to address these problems by following the trend of coverage-based fuzzing. However, new coverage metrics on DNNs may bring out the question of which layer to measure the coverage in DNNs. In this poster, we empirically evaluate the performance of existing coverage metrics. By the comparative analysis of experimental results, we compile the most effective layer for each of coverage metrics and discuss a future direction of DNN fuzzing.

UR - http://www.scopus.com/inward/record.url?scp=85075944919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075944919&partnerID=8YFLogxK

U2 - 10.1145/3319535.3363286

DO - 10.1145/3319535.3363286

M3 - Conference contribution

AN - SCOPUS:85075944919

T3 - Proceedings of the ACM Conference on Computer and Communications Security

SP - 2681

EP - 2683

BT - CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security

PB - Association for Computing Machinery

Y2 - 11 November 2019 through 15 November 2019

ER -

Park LH, Oh S, Kim J, Chung S, Kwon T. Poster: Effective layers in coverage metrics for deep neural networks. In CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security. Association for Computing Machinery. 2019. p. 2681-2683. (Proceedings of the ACM Conference on Computer and Communications Security). doi: 10.1145/3319535.3363286

Poster: Effective layers in coverage metrics for deep neural networks

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this