Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

On the vulnerability of data-driven structural health monitoring models to adversarial attack

Journal Article · · Structural Health Monitoring
 [1];  [2];  [2];  [2];  [2]
  1. Industrial Doctorate Centre in Machining Science, The University of Sheffield – Advanced Manufacturing Research Centre with Boeing (AMRC), Rotherham, UK, Dynamics Research Group, The University of Sheffield, Sheffield, UK
  2. Los Alamos National Laboratory, Los Alamos, NM, USA

Many approaches at the forefront of structural health monitoring rely on cutting-edge techniques from the field of machine learning. Recently, much interest has been directed towards the study of so-called adversarial examples; deliberate input perturbations that deceive machine learning models while remaining semantically identical. This article demonstrates that data-driven approaches to structural health monitoring are vulnerable to attacks of this kind. In the perfect information or ‘white-box’ scenario, a transformation is found that maps every example in the Los Alamos National Laboratory three-storey structure dataset to an adversarial example. Also presented is an adversarial threat model specific to structural health monitoring. The threat model is proposed with a view to motivate discussion into ways in which structural health monitoring approaches might be made more robust to the threat of adversarial attack.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE; USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
89233218CNA000001
OSTI ID:
1630947
Alternate ID(s):
OSTI ID: 1822742
Report Number(s):
LA-UR--19-32456
Journal Information:
Structural Health Monitoring, Journal Name: Structural Health Monitoring Journal Issue: 4 Vol. 20; ISSN 1475-9217
Publisher:
SAGE PublicationsCopyright Statement
Country of Publication:
United Kingdom
Language:
English

References (20)

Structural Health Monitoring book November 2012
An approach to decision‐making analysis for implementation of structural health monitoring in bridges journal March 2019
Experimental Validation of a Structural Health Monitoring Methodology: part iii. Damage Location on an Aircraft wing journal January 2003
Damage Assessment Using Neural Networks journal January 2003
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities book January 2015
An outlier analysis framework for impedance-based structural health monitoring journal August 2005
Structural health monitoring of offshore wind turbines: A review through the Statistical Pattern Recognition Paradigm journal October 2016
The fundamental axioms of structural health monitoring
  • Worden, Keith; Farrar, Charles R.; Manson, Graeme
  • Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 463, Issue 2082 https://doi.org/10.1098/rspa.2007.1834
journal March 2007
Vibration–based structural damage identification
  • Farrar, Charles R.; Doebling, Scott W.; Nix, David A.
  • Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, Vol. 359, Issue 1778 https://doi.org/10.1098/rsta.2000.0717
journal January 2001
The application of machine learning to structural health monitoring
  • Worden, Keith; Manson, Graeme
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 365, Issue 1851 https://doi.org/10.1098/rsta.2006.1938
journal December 2006
Self-adaptive Differential Evolution Algorithm for Numerical Optimization conference January 2005
Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks: Deep learning-based crack damage detection using CNNs journal March 2017
Structural Health Monitoring With Autoregressive Support Vector Machines journal February 2009
ICAS: the center of diagnostics and prognostics for the United States Navy conference July 2001
Reducing the Dimensionality of Data with Neural Networks journal July 2006
Toward a threat model for storage systems conference November 2005
Practical Black-Box Attacks against Machine Learning
  • Papernot, Nicolas; McDaniel, Patrick; Goodfellow, Ian
  • ASIA CCS '17: ACM Asia Conference on Computer and Communications Security, Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security https://doi.org/10.1145/3052973.3053009
conference April 2017
Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
  • Carlini, Nicholas; Wagner, David
  • CCS '17: 2017 ACM SIGSAC Conference on Computer and Communications Security, Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security https://doi.org/10.1145/3128572.3140444
conference November 2017
Structural health monitoring algorithm comparisons using standard data sets report March 2009
Deep Learning for Structural Health Monitoring: A Damage Characterization Application journal October 2016

Similar Records

Defending Against Adversarial Examples
Technical Report · Sun Sep 01 00:00:00 EDT 2019 · OSTI ID:1569514

Transferable Adversarial Attack on 3D Object Tracking in Point Cloud
Conference · Sun Jan 08 23:00:00 EST 2023 · OSTI ID:1993156