Vibrational Spectroscopy Can Be Vulnerable to Adversarial Attacks
- 11 October 2024
- journal article
- research article
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 96 (42) , 16570-16580
Abstract
Nondestructive detection methods based on vibrational spectroscopy have been widely used in many critical applications in a variety of fields such as the chemical industry, pharmacy, national defense, security, and so on. As these methods/applications rely on machine learning models for data analysis, studying the threats associated with adversarial examples in vibrational spectroscopy and defenses against them is of great importance. In this paper, we propose a novel adversarial method to attack vibrational spectroscopy, named SynPat, where synthetic peaks produced by a physical model are placed at key locations to form adversarial perturbations. Our new attack generates perturbations that successfully deceive machine learning models for Raman and infrared spectrum analysis while they blend much better into the spectra and hence are unnoticeable to human operators, unlike the existing state-of-the-art adversarial attacking methods, e.g., images and audio. We verified the superiority of the proposed SynPat by an imperceptibility test conducted by human experts and of defense experiments by an AI detector. To the best of our knowledge, this is a first thorough study on the robustness of vibrational spectroscopic techniques against adversarial samples and defense mechanisms. Our extensive experiments show that machine learning models for vibrational spectroscopy, including conventional and deep models for Raman or infrared classification and regression, are all vulnerable to adversarial perturbations and thus may pose serious security threats to our society.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB4703204)
- National Natural Science Foundation of China (62076140, 62233011)
This publication has 39 references indexed in Scilit:
- Deep metric learning framework combined with Gramian angular difference field image generation for Raman spectra classification based on a handheld Raman spectrometerSpectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2023
- Spectral classification by generative adversarial linear discriminant analysisAnalytica Chimica Acta, 2023
- Ultra-fast and onsite interrogation of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) in waters via surface enhanced Raman scattering (SERS)Water Research, 2021
- Feature visualization of Raman spectrum analysis with deep convolutional neural networkAnalytica Chimica Acta, 2019
- Using deep learning to predict soil properties from regional spectral dataGeoderma Regional, 2019
- Machine-Learning-Driven Surface-Enhanced Raman Scattering Optophysiology Reveals Multiplexed Metabolite Gradients Near CellsACS Nano, 2019
- Dynamic spectrum matching with one-shot learningChemometrics and Intelligent Laboratory Systems, 2019
- Hierarchical deep convolutional neural networks combine spectral and spatial information for highly accurate Raman‐microscopy‐based cytopathologyJournal of Biophotonics, 2018
- Rapid Detection of Drugs of Abuse in Saliva Using Surface Enhanced Raman Spectroscopy and MicrofluidicsACS Nano, 2013
- The LUCAS topsoil database and derived information on the regional variability of cropland topsoil properties in the European UnionEnvironmental Monitoring and Assessment, 2013