AVERAGER STUDENT: DISTILLATION FROM UNDISTILLABLE TEACHER

Reyhan Kevser Keser; Behçet Ugur Töreyin

AVERAGER STUDENT: DISTILLATION FROM UNDISTILLABLE TEACHER

Bilişim Enstitüsü

Araştırma sonucu: Konferansa katkı › Yazı › bilirkişi

1 Atıf (Scopus)

Özet

Today, some companies release their black-box model as a service for users, where users can see the model’s output corresponding to their input. However, these models can be stolen via knowledge distillation by malicious users. Recently, undistillable teacher (Ma et al., 2021) is introduced in order to prevent the knowledge leakage. In this study, with the aim of contributing to solutions for model intellectual property (IP) protection, we propose a novel method which improves the distillation from an undistillable teacher whose goal is make the distillation difficult for students, with the purpose of model protection. The codes are released at https://github.com/rkevser/AveragerStudent.

Orijinal dil	İngilizce
Yayın durumu	Yayınlandı - 2023
Etkinlik	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 - Kigali, Rwanda Süre: 5 May 2023 → 5 May 2023

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Ülke/Bölge	Rwanda
Şehir	Kigali
Periyot	5/05/23 → 5/05/23

Bibliyografik not

Publisher Copyright:
© 2023 1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023. All rights reserved.

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

@conference{510a42fb522847e9b98768e63ec3d83d,

title = "AVERAGER STUDENT: DISTILLATION FROM UNDISTILLABLE TEACHER",

abstract = "Today, some companies release their black-box model as a service for users, where users can see the model{\textquoteright}s output corresponding to their input. However, these models can be stolen via knowledge distillation by malicious users. Recently, undistillable teacher (Ma et al., 2021) is introduced in order to prevent the knowledge leakage. In this study, with the aim of contributing to solutions for model intellectual property (IP) protection, we propose a novel method which improves the distillation from an undistillable teacher whose goal is make the distillation difficult for students, with the purpose of model protection. The codes are released at https://github.com/rkevser/AveragerStudent.",

author = "Keser, \{Reyhan Kevser\} and T{\"o}reyin, \{Beh{\c c}et Ugur\}",

note = "Publisher Copyright: {\textcopyright} 2023 1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023. All rights reserved.; 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 ; Conference date: 05-05-2023 Through 05-05-2023",

year = "2023",

language = "English",

}

TY - CONF

T1 - AVERAGER STUDENT

T2 - 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023

AU - Keser, Reyhan Kevser

AU - Töreyin, Behçet Ugur

PY - 2023

Y1 - 2023

N2 - Today, some companies release their black-box model as a service for users, where users can see the model’s output corresponding to their input. However, these models can be stolen via knowledge distillation by malicious users. Recently, undistillable teacher (Ma et al., 2021) is introduced in order to prevent the knowledge leakage. In this study, with the aim of contributing to solutions for model intellectual property (IP) protection, we propose a novel method which improves the distillation from an undistillable teacher whose goal is make the distillation difficult for students, with the purpose of model protection. The codes are released at https://github.com/rkevser/AveragerStudent.

AB - Today, some companies release their black-box model as a service for users, where users can see the model’s output corresponding to their input. However, these models can be stolen via knowledge distillation by malicious users. Recently, undistillable teacher (Ma et al., 2021) is introduced in order to prevent the knowledge leakage. In this study, with the aim of contributing to solutions for model intellectual property (IP) protection, we propose a novel method which improves the distillation from an undistillable teacher whose goal is make the distillation difficult for students, with the purpose of model protection. The codes are released at https://github.com/rkevser/AveragerStudent.

UR - https://www.scopus.com/pages/publications/105026756305

M3 - Paper

AN - SCOPUS:105026756305

Y2 - 5 May 2023 through 5 May 2023

ER -

AVERAGER STUDENT: DISTILLATION FROM UNDISTILLABLE TEACHER

Özet

???event.eventtypes.event.conference???

Bibliyografik not

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap