Presentation 2018-03-02
Modeling Attacks on Double-Arbiter PUF Using Deep Neural Network
Tomoki Iizuka, Hiromitsu Awano, Makoto Ikeda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A deep neural network-based modeling attack for Double-Arbiter PUF (DAPUF) is proposed. Although DAPUF is known to be highly resistant to modeling attacks, by employing some novel techniques developped in machine learning community, such as ReLU activation function and Xavier initialization technique, our model succcessfly predicted responses to unseen challenges with probability of 88.4%, which is 21.1% higher than the conventional method. Those results highlight an important fact that PUF-based authentication schemes should be carefully designed considering the rapid evoluving machine learning technology.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) PUF / Double-Arbiter PUF / deep neural network / machine learning attack / modeling attack
Paper # VLD2017-127
Date of Issue 2018-02-21 (VLD)

Conference Information
Committee VLD / HWS
Conference Date 2018/2/28(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Seinen Kaikan
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroyuki Ochi(Ritsumeikan Univ.)
Vice Chair Noriyuki Minegishi(Mitsubishi Electric)
Secretary Noriyuki Minegishi(Hiroshima City Univ.) / (NTT)
Assistant

Paper Information
Registration To Technical Committee on VLSI Design Technologies / Technical Committee on Hardware Security
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Modeling Attacks on Double-Arbiter PUF Using Deep Neural Network
Sub Title (in English)
Keyword(1) PUF
Keyword(2) Double-Arbiter PUF
Keyword(3) deep neural network
Keyword(4) machine learning attack
Keyword(5) modeling attack
1st Author's Name Tomoki Iizuka
1st Author's Affiliation The University of Tokyo(UTokyo)
2nd Author's Name Hiromitsu Awano
2nd Author's Affiliation The University of Tokyo(UTokyo)
3rd Author's Name Makoto Ikeda
3rd Author's Affiliation The University of Tokyo(UTokyo)
Date 2018-03-02
Paper # VLD2017-127
Volume (vol) vol.117
Number (no) VLD-455
Page pp.pp.231-236(VLD),
#Pages 6
Date of Issue 2018-02-21 (VLD)