The fake vs real goods problem

Microscopy and machine learning to the rescue

Ashlesh Sharma, Vidyuth Srinivasan, Vishal Kanchan, Lakshminarayanan Subramanian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Counterfeiting of physical goods is a global problem amounting to nearly 7% of world trade. While there have been a variety of overt technologies like holograms and specialized barcodes and covert technologies like taggants and PUFs, these solutions have had a limited impact on the counterfeit market due to a variety of factors - clonability, cost or adoption barriers. In this paper, we introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classification engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for "super-fake" counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verification ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classification accuracy is more than 98% and we show how our system works with a cellphone to verify the authenticity of everyday objects.

Original languageEnglish (US)
Title of host publicationKDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages2011-2019
Number of pages9
VolumePart F129685
ISBN (Electronic)9781450348874
DOIs
StatePublished - Aug 13 2017
Event23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017 - Halifax, Canada
Duration: Aug 13 2017Aug 17 2017

Other

Other23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017
CountryCanada
CityHalifax
Period8/13/178/17/17

Fingerprint

Mobile devices
Learning algorithms
Learning systems
Microscopic examination
Leather
Holograms
Ecosystems
Authentication
Electronic equipment
Engines
Hardware
Costs

Keywords

  • Computer vision
  • Convolutional neural networks
  • Microscopy
  • Physical authentication

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Sharma, A., Srinivasan, V., Kanchan, V., & Subramanian, L. (2017). The fake vs real goods problem: Microscopy and machine learning to the rescue. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. Part F129685, pp. 2011-2019). Association for Computing Machinery. https://doi.org/10.1145/3097983.3098186

The fake vs real goods problem : Microscopy and machine learning to the rescue. / Sharma, Ashlesh; Srinivasan, Vidyuth; Kanchan, Vishal; Subramanian, Lakshminarayanan.

KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. p. 2011-2019.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sharma, A, Srinivasan, V, Kanchan, V & Subramanian, L 2017, The fake vs real goods problem: Microscopy and machine learning to the rescue. in KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. Part F129685, Association for Computing Machinery, pp. 2011-2019, 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, Halifax, Canada, 8/13/17. https://doi.org/10.1145/3097983.3098186
Sharma A, Srinivasan V, Kanchan V, Subramanian L. The fake vs real goods problem: Microscopy and machine learning to the rescue. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685. Association for Computing Machinery. 2017. p. 2011-2019 https://doi.org/10.1145/3097983.3098186
Sharma, Ashlesh ; Srinivasan, Vidyuth ; Kanchan, Vishal ; Subramanian, Lakshminarayanan. / The fake vs real goods problem : Microscopy and machine learning to the rescue. KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. pp. 2011-2019
@inproceedings{d45fa787e43341538b8d9aa6e9f3dd8b,
title = "The fake vs real goods problem: Microscopy and machine learning to the rescue",
abstract = "Counterfeiting of physical goods is a global problem amounting to nearly 7{\%} of world trade. While there have been a variety of overt technologies like holograms and specialized barcodes and covert technologies like taggants and PUFs, these solutions have had a limited impact on the counterfeit market due to a variety of factors - clonability, cost or adoption barriers. In this paper, we introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classification engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for {"}super-fake{"} counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verification ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classification accuracy is more than 98{\%} and we show how our system works with a cellphone to verify the authenticity of everyday objects.",
keywords = "Computer vision, Convolutional neural networks, Microscopy, Physical authentication",
author = "Ashlesh Sharma and Vidyuth Srinivasan and Vishal Kanchan and Lakshminarayanan Subramanian",
year = "2017",
month = "8",
day = "13",
doi = "10.1145/3097983.3098186",
language = "English (US)",
volume = "Part F129685",
pages = "2011--2019",
booktitle = "KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - The fake vs real goods problem

T2 - Microscopy and machine learning to the rescue

AU - Sharma, Ashlesh

AU - Srinivasan, Vidyuth

AU - Kanchan, Vishal

AU - Subramanian, Lakshminarayanan

PY - 2017/8/13

Y1 - 2017/8/13

N2 - Counterfeiting of physical goods is a global problem amounting to nearly 7% of world trade. While there have been a variety of overt technologies like holograms and specialized barcodes and covert technologies like taggants and PUFs, these solutions have had a limited impact on the counterfeit market due to a variety of factors - clonability, cost or adoption barriers. In this paper, we introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classification engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for "super-fake" counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verification ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classification accuracy is more than 98% and we show how our system works with a cellphone to verify the authenticity of everyday objects.

AB - Counterfeiting of physical goods is a global problem amounting to nearly 7% of world trade. While there have been a variety of overt technologies like holograms and specialized barcodes and covert technologies like taggants and PUFs, these solutions have had a limited impact on the counterfeit market due to a variety of factors - clonability, cost or adoption barriers. In this paper, we introduce a new mechanism that uses machine learning algorithms on microscopic images of physical objects to distinguish between genuine and counterfeit versions of the same product. The underlying principle of our system stems from the idea that microscopic characteristics in a genuine product or a class of products (corresponding to the same larger product line), exhibit inherent similarities that can be used to distinguish these products from their corresponding counterfeit versions. A key building block for our system is a wide-angle microscopy device compatible with a mobile device that enables a user to easily capture the microscopic image of a large area of a physical object. Based on the captured microscopic images, we show that using machine learning algorithms (ConvNets and bag of words), one can generate a highly accurate classification engine for separating the genuine versions of a product from the counterfeit ones; this property also holds for "super-fake" counterfeits observed in the marketplace that are not easily discernible from the human eye. We describe the design of an end-to-end physical authentication system leveraging mobile devices, portable hardware and a cloud-based object verification ecosystem. We evaluate our system using a large dataset of 3 million images across various objects and materials such as fabrics, leather, pills, electronics, toys and shoes. The classification accuracy is more than 98% and we show how our system works with a cellphone to verify the authenticity of everyday objects.

KW - Computer vision

KW - Convolutional neural networks

KW - Microscopy

KW - Physical authentication

UR - http://www.scopus.com/inward/record.url?scp=85029080133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029080133&partnerID=8YFLogxK

U2 - 10.1145/3097983.3098186

DO - 10.1145/3097983.3098186

M3 - Conference contribution

VL - Part F129685

SP - 2011

EP - 2019

BT - KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -