The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
조회수
115
고성능 센서와 소셜네트워크서비스(SNS)의 확산과 머신러닝 기술의 눈부신 발전으로 고품질의 학습 데이터를 이용해 생성된 가짜 동영상, 스푸핑된 음성, 가짜 리뷰 등 가짜 미디어가 매우 밀접하게 실제로 심각한 사회 문제를 일으키고 있습니다. 우리는 미디어 처리 기술을 통해 능숙하게 제작된 미디어 클론(MC)이라고 불리는 실제 미디어의 복제물 수신자를 보호하기 위한 연구 프로젝트인 미디어 클론(MC) 프로젝트를 시작했습니다. 우리의 목표는 MC 공격을 방어하고 안전하고 안정적인 통신을 보장할 수 있는 통신 시스템을 구축하는 것입니다. 본 논문은 MC 프로젝트의 1가지 주제 중 2) 가짜 정보로부터 파생된 오디오, 비주얼, 텍스트 등 다양한 형태의 미디어 클론 생성 능력 검증, XNUMX) 보호 실현이라는 XNUMX가지 주제에 대한 연구 결과를 기술하고 있다. 미디어 클론의 공격을 인식하여 방어합니다.
Isao ECHIZEN
National Institute of Informatics
Noboru BABAGUCHI
Osaka University
Junichi YAMAGISHI
National Institute of Informatics
Naoko NITTA
Osaka University
Yuta NAKASHIMA
Osaka University
Kazuaki NAKAMURA
Osaka University
Kazuhiro KONO
Kansai University
Fuming FANG
National Institute of Informatics
Seiko MYOJIN
Osaka University
Zhenzhong KUANG
Osaka University
Huy H. NGUYEN
National Institute of Informatics
Ngoc-Dung T. TIEU
National Institute of Informatics
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Isao ECHIZEN, Noboru BABAGUCHI, Junichi YAMAGISHI, Naoko NITTA, Yuta NAKASHIMA, Kazuaki NAKAMURA, Kazuhiro KONO, Fuming FANG, Seiko MYOJIN, Zhenzhong KUANG, Huy H. NGUYEN, Ngoc-Dung T. TIEU, "Generation and Detection of Media Clones" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 1, pp. 12-23, January 2021, doi: 10.1587/transinf.2020MUI0002.
Abstract: With the spread of high-performance sensors and social network services (SNS) and the remarkable advances in machine learning technologies, fake media such as fake videos, spoofed voices, and fake reviews that are generated using high-quality learning data and are very close to the real thing are causing serious social problems. We launched a research project, the Media Clone (MC) project, to protect receivers of replicas of real media called media clones (MCs) skillfully fabricated by means of media processing technologies. Our aim is to achieve a communication system that can defend against MC attacks and help ensure safe and reliable communication. This paper describes the results of research in two of the five themes in the MC project: 1) verification of the capability of generating various types of media clones such as audio, visual, and text derived from fake information and 2) realization of a protection shield for media clones' attacks by recognizing them.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020MUI0002/_p
부
@ARTICLE{e104-d_1_12,
author={Isao ECHIZEN, Noboru BABAGUCHI, Junichi YAMAGISHI, Naoko NITTA, Yuta NAKASHIMA, Kazuaki NAKAMURA, Kazuhiro KONO, Fuming FANG, Seiko MYOJIN, Zhenzhong KUANG, Huy H. NGUYEN, Ngoc-Dung T. TIEU, },
journal={IEICE TRANSACTIONS on Information},
title={Generation and Detection of Media Clones},
year={2021},
volume={E104-D},
number={1},
pages={12-23},
abstract={With the spread of high-performance sensors and social network services (SNS) and the remarkable advances in machine learning technologies, fake media such as fake videos, spoofed voices, and fake reviews that are generated using high-quality learning data and are very close to the real thing are causing serious social problems. We launched a research project, the Media Clone (MC) project, to protect receivers of replicas of real media called media clones (MCs) skillfully fabricated by means of media processing technologies. Our aim is to achieve a communication system that can defend against MC attacks and help ensure safe and reliable communication. This paper describes the results of research in two of the five themes in the MC project: 1) verification of the capability of generating various types of media clones such as audio, visual, and text derived from fake information and 2) realization of a protection shield for media clones' attacks by recognizing them.},
keywords={},
doi={10.1587/transinf.2020MUI0002},
ISSN={1745-1361},
month={January},}
부
TY - JOUR
TI - Generation and Detection of Media Clones
T2 - IEICE TRANSACTIONS on Information
SP - 12
EP - 23
AU - Isao ECHIZEN
AU - Noboru BABAGUCHI
AU - Junichi YAMAGISHI
AU - Naoko NITTA
AU - Yuta NAKASHIMA
AU - Kazuaki NAKAMURA
AU - Kazuhiro KONO
AU - Fuming FANG
AU - Seiko MYOJIN
AU - Zhenzhong KUANG
AU - Huy H. NGUYEN
AU - Ngoc-Dung T. TIEU
PY - 2021
DO - 10.1587/transinf.2020MUI0002
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2021
AB - With the spread of high-performance sensors and social network services (SNS) and the remarkable advances in machine learning technologies, fake media such as fake videos, spoofed voices, and fake reviews that are generated using high-quality learning data and are very close to the real thing are causing serious social problems. We launched a research project, the Media Clone (MC) project, to protect receivers of replicas of real media called media clones (MCs) skillfully fabricated by means of media processing technologies. Our aim is to achieve a communication system that can defend against MC attacks and help ensure safe and reliable communication. This paper describes the results of research in two of the five themes in the MC project: 1) verification of the capability of generating various types of media clones such as audio, visual, and text derived from fake information and 2) realization of a protection shield for media clones' attacks by recognizing them.
ER -