Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models

Srikanth Yoginath; Michael Iannacone; Varisara Tansakul; Ali Passian; Rob Jordan; Joel Asiamah; M. Nance Ericson; Gavin Long; Joel A. Dawson

doi:10.1145/3560833.3563564

Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models

Srikanth Yoginath, Michael Iannacone, Varisara Tansakul, Ali Passian, Rob Jordan, Joel Asiamah, M. Nance Ericson, Gavin Long, Joel A. Dawson

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

1 Scopus citations

Abstract

As Additive Layer Manufacturing (ALM) becomes pervasive in industry, its applications in safety critical component manufacturing are being explored and adopted. However, ALM's reliance on embedded computing renders it vulnerable to tampering through cyber-attacks. Sensor instrumentation of ALM devices allows for rigorous process and security monitoring, but also results in a massive volume of noisy data for each run. As such, in-situ, near-real-time anomaly detection is very challenging. The ideal algorithm for this context is simple, computationally efficient, minimizes false positives, and is accurate enough to resolve small deviations. In this paper, we present a probabilistic-model-based approach to address this challenge. To test our approach, we analyze current measurements from a polymer composite 3D printer during emulated tampering attacks. Our results show that our approach can consistently and efficiently locate small changes in the presence of substantial operational noise.

Original language	English
Title of host publication	AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022
Publisher	Association for Computing Machinery, Inc
Pages	25-38
Number of pages	14
ISBN (Electronic)	9781450398831
DOIs	https://doi.org/10.1145/3560833.3563564
State	Published - Nov 11 2022
Event	2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, AMSec 2022 - Co-located with CCS 2022 - Los Angeles, United States Duration: Nov 11 2022 → …

Publication series

Name	AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022

Conference

Conference	2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, AMSec 2022 - Co-located with CCS 2022
Country/Territory	United States
City	Los Angeles
Period	11/11/22 → …

Funding

This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Funders	Funder number
U.S. Department of Energy

Keywords

additive layer manufacturing
anomaly detection
bayesian inference
cyber-physical system security
markov chain monte carlo

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3560833.3563564

Cite this

Yoginath, S., Iannacone, M., Tansakul, V., Passian, A., Jordan, R., Asiamah, J., Nance Ericson, M., Long, G., & Dawson, J. A. (2022). Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models. In AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022 (pp. 25-38). (AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022). Association for Computing Machinery, Inc. https://doi.org/10.1145/3560833.3563564

Yoginath, Srikanth ; Iannacone, Michael ; Tansakul, Varisara et al. / Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models. AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022. Association for Computing Machinery, Inc, 2022. pp. 25-38 (AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022).

@inproceedings{727b610de9444d7d97c3b74e180e6606,

title = "Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models",

abstract = "As Additive Layer Manufacturing (ALM) becomes pervasive in industry, its applications in safety critical component manufacturing are being explored and adopted. However, ALM's reliance on embedded computing renders it vulnerable to tampering through cyber-attacks. Sensor instrumentation of ALM devices allows for rigorous process and security monitoring, but also results in a massive volume of noisy data for each run. As such, in-situ, near-real-time anomaly detection is very challenging. The ideal algorithm for this context is simple, computationally efficient, minimizes false positives, and is accurate enough to resolve small deviations. In this paper, we present a probabilistic-model-based approach to address this challenge. To test our approach, we analyze current measurements from a polymer composite 3D printer during emulated tampering attacks. Our results show that our approach can consistently and efficiently locate small changes in the presence of substantial operational noise.",

keywords = "additive layer manufacturing, anomaly detection, bayesian inference, cyber-physical system security, markov chain monte carlo",

author = "Srikanth Yoginath and Michael Iannacone and Varisara Tansakul and Ali Passian and Rob Jordan and Joel Asiamah and {Nance Ericson}, M. and Gavin Long and Dawson, {Joel A.}",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, AMSec 2022 - Co-located with CCS 2022 ; Conference date: 11-11-2022",

year = "2022",

month = nov,

day = "11",

doi = "10.1145/3560833.3563564",

language = "English",

series = "AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022",

publisher = "Association for Computing Machinery, Inc",

pages = "25--38",

booktitle = "AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022",

}

Yoginath, S, Iannacone, M, Tansakul, V, Passian, A, Jordan, R, Asiamah, J, Nance Ericson, M, Long, G & Dawson, JA 2022, Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models. in AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022. AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022, Association for Computing Machinery, Inc, pp. 25-38, 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, AMSec 2022 - Co-located with CCS 2022, Los Angeles, United States, 11/11/22. https://doi.org/10.1145/3560833.3563564

Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models. / Yoginath, Srikanth; Iannacone, Michael; Tansakul, Varisara et al.
AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022. Association for Computing Machinery, Inc, 2022. p. 25-38 (AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022).

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

TY - GEN

T1 - Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models

AU - Yoginath, Srikanth

AU - Iannacone, Michael

AU - Tansakul, Varisara

AU - Passian, Ali

AU - Jordan, Rob

AU - Asiamah, Joel

AU - Nance Ericson, M.

AU - Long, Gavin

AU - Dawson, Joel A.

PY - 2022/11/11

Y1 - 2022/11/11

N2 - As Additive Layer Manufacturing (ALM) becomes pervasive in industry, its applications in safety critical component manufacturing are being explored and adopted. However, ALM's reliance on embedded computing renders it vulnerable to tampering through cyber-attacks. Sensor instrumentation of ALM devices allows for rigorous process and security monitoring, but also results in a massive volume of noisy data for each run. As such, in-situ, near-real-time anomaly detection is very challenging. The ideal algorithm for this context is simple, computationally efficient, minimizes false positives, and is accurate enough to resolve small deviations. In this paper, we present a probabilistic-model-based approach to address this challenge. To test our approach, we analyze current measurements from a polymer composite 3D printer during emulated tampering attacks. Our results show that our approach can consistently and efficiently locate small changes in the presence of substantial operational noise.

AB - As Additive Layer Manufacturing (ALM) becomes pervasive in industry, its applications in safety critical component manufacturing are being explored and adopted. However, ALM's reliance on embedded computing renders it vulnerable to tampering through cyber-attacks. Sensor instrumentation of ALM devices allows for rigorous process and security monitoring, but also results in a massive volume of noisy data for each run. As such, in-situ, near-real-time anomaly detection is very challenging. The ideal algorithm for this context is simple, computationally efficient, minimizes false positives, and is accurate enough to resolve small deviations. In this paper, we present a probabilistic-model-based approach to address this challenge. To test our approach, we analyze current measurements from a polymer composite 3D printer during emulated tampering attacks. Our results show that our approach can consistently and efficiently locate small changes in the presence of substantial operational noise.

KW - additive layer manufacturing

KW - anomaly detection

KW - bayesian inference

KW - cyber-physical system security

KW - markov chain monte carlo

UR - http://www.scopus.com/inward/record.url?scp=85145572696&partnerID=8YFLogxK

U2 - 10.1145/3560833.3563564

DO - 10.1145/3560833.3563564

M3 - Conference contribution

AN - SCOPUS:85145572696

T3 - AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022

SP - 25

EP - 38

BT - AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022

PB - Association for Computing Machinery, Inc

T2 - 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, AMSec 2022 - Co-located with CCS 2022

Y2 - 11 November 2022

ER -

Yoginath S, Iannacone M, Tansakul V, Passian A, Jordan R, Asiamah J et al. Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models. In AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022. Association for Computing Machinery, Inc. 2022. p. 25-38. (AMSec 2022 - Proceedings of the 2022 ACM CCS Workshop on Additive Manufacturing ,3D Printing Security, co-located with CCS 2022). doi: 10.1145/3560833.3563564

Stealthy Cyber Anomaly Detection On Large Noisy Multi-material 3D Printer Datasets Using Probabilistic Models

Abstract

Publication series

Conference

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this