TY - GEN
T1 - Bio-FP
T2 - 2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023
AU - Baban, Navajit Singh
AU - Saha, Sohini
AU - Jancheska, Sofija
AU - Zhou, Jiarui
AU - Vijayavenkataraman, Sanjairaj
AU - Bhattacharjee, Sukanta
AU - Song, Yong Ak
AU - Chakrabarty, Krishnendu
AU - Karri, Ramesh
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Microfluidic biochips are widely used in biological computing, clinical diagnostics, and point-of-care tests. However, the growing demand and the complex supply chain of biochips expose them to intellectual property (IP) attacks such as counterfeiting, overbuilding, and piracy. To address this issue, we present a biochip-level fingerprinting (Bio-FP) scheme. We utilize melt-electrospinning printing technique to print unique Bio-FPs directly onto biochips. Then, a layer of polydimethylsiloxane (PDMS) is applied through spin-coating to obscure the Bio-FPs. If the Bio-FPs are doped with a fluorescent dye, they can be detected by shining UV light. Authentication of dyed Bio-FPs is achieved through spectral analysis by mapping the intensitywavelength response. To optimize the authentication scheme for Bio-FPs, several pre-processing techniques were employed to enhance their quality. Additionally, transfer learning and finetuning were utilized with multiple deep learning models, yielding a high Bio-FP classification accuracy of 95.8%.
AB - Microfluidic biochips are widely used in biological computing, clinical diagnostics, and point-of-care tests. However, the growing demand and the complex supply chain of biochips expose them to intellectual property (IP) attacks such as counterfeiting, overbuilding, and piracy. To address this issue, we present a biochip-level fingerprinting (Bio-FP) scheme. We utilize melt-electrospinning printing technique to print unique Bio-FPs directly onto biochips. Then, a layer of polydimethylsiloxane (PDMS) is applied through spin-coating to obscure the Bio-FPs. If the Bio-FPs are doped with a fluorescent dye, they can be detected by shining UV light. Authentication of dyed Bio-FPs is achieved through spectral analysis by mapping the intensitywavelength response. To optimize the authentication scheme for Bio-FPs, several pre-processing techniques were employed to enhance their quality. Additionally, transfer learning and finetuning were utilized with multiple deep learning models, yielding a high Bio-FP classification accuracy of 95.8%.
KW - biochip
KW - counterfeiting
KW - deep learning
KW - fingerprints
KW - intellectual property
KW - melt electrospinning
UR - http://www.scopus.com/inward/record.url?scp=85184909377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85184909377&partnerID=8YFLogxK
U2 - 10.1109/BioCAS58349.2023.10388991
DO - 10.1109/BioCAS58349.2023.10388991
M3 - Conference contribution
AN - SCOPUS:85184909377
T3 - BioCAS 2023 - 2023 IEEE Biomedical Circuits and Systems Conference, Conference Proceedings
BT - BioCAS 2023 - 2023 IEEE Biomedical Circuits and Systems Conference, Conference Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 October 2023 through 21 October 2023
ER -