WEKO3
アイテム
Development and Trial Application of an Improved MRC-EDC Method for Risk Assessment of Attacks on Humans by Generative AI
https://ipsj.ixsq.nii.ac.jp/records/241743
https://ipsj.ixsq.nii.ac.jp/records/24174313dc8da0-3bf5-471a-9e9a-f2d8bfb2e96d
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]()
2026年12月14日からダウンロード可能です。
|
Copyright (c) 2024 by the Information Processing Society of Japan
|
|
非会員:¥0, IPSJ:学会員:¥0, 論文誌:会員:¥0, DLIB:会員:¥0 |
Item type | Journal(1) | |||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2024-12-15 | |||||||||||||
タイトル | ||||||||||||||
タイトル | Development and Trial Application of an Improved MRC-EDC Method for Risk Assessment of Attacks on Humans by Generative AI | |||||||||||||
タイトル | ||||||||||||||
言語 | en | |||||||||||||
タイトル | Development and Trial Application of an Improved MRC-EDC Method for Risk Assessment of Attacks on Humans by Generative AI | |||||||||||||
言語 | ||||||||||||||
言語 | eng | |||||||||||||
キーワード | ||||||||||||||
主題Scheme | Other | |||||||||||||
主題 | [特集:社会的・倫理的なオンライン活動を支援するセキュリティとトラスト] generative AI, security, risk assessment, risk communication, AI attacks | |||||||||||||
資源タイプ | ||||||||||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
資源タイプ | journal article | |||||||||||||
著者所属 | ||||||||||||||
Tokyo Denki University | ||||||||||||||
著者所属 | ||||||||||||||
PwC Consulting LLC | ||||||||||||||
著者所属 | ||||||||||||||
PwC Consulting LLC | ||||||||||||||
著者所属 | ||||||||||||||
Tokyo Denki University | ||||||||||||||
著者所属(英) | ||||||||||||||
en | ||||||||||||||
Tokyo Denki University | ||||||||||||||
著者所属(英) | ||||||||||||||
en | ||||||||||||||
PwC Consulting LLC | ||||||||||||||
著者所属(英) | ||||||||||||||
en | ||||||||||||||
PwC Consulting LLC | ||||||||||||||
著者所属(英) | ||||||||||||||
en | ||||||||||||||
Tokyo Denki University | ||||||||||||||
著者名 |
Ryoichi, Sasaki
× Ryoichi, Sasaki
× Kenta, Onishi
× Yoshihiro, Mitsui
× Masato, Terada
|
|||||||||||||
著者名(英) |
Ryoichi, Sasaki
× Ryoichi, Sasaki
× Kenta, Onishi
× Yoshihiro, Mitsui
× Masato, Terada
|
|||||||||||||
論文抄録 | ||||||||||||||
内容記述タイプ | Other | |||||||||||||
内容記述 | The authors previously proposed classifying the relationship between AI and security into four types: attacks using AI, attacks by AI, attacks to AI, and security measures using AI. Subsequently, generative AI such as ChatGPT has become widely used. Therefore, we examined the impact of the emergence of generative AI on the relationship between AI and security and demonstrated a pressing need for countermeasures against attacks by generative AI. The authors then categorized three types of attacks from generative AI to humans: “Terminator,” “2001: A Space Odyssey,” and “Mad Scientist,” and proposed potential countermeasures against them. The MRC-EDC method developed earlier by the authors aimed to optimize the combination of countermeasures, but it was not suitable for this subject due to its full-quantitative approach, necessitating rigorous cost and risk estimation. Consequently, we developed an improved MRC-EDC method that partially incorporates a semi-quantitative approach and conducted a trial to propose countermeasures against attacks by generative AI. As a result, five cost-effective countermeasures were identified, confirming the effectiveness of this method. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) DOI http://dx.doi.org/10.2197/ipsjjip.32.1057 ------------------------------ |
|||||||||||||
論文抄録(英) | ||||||||||||||
内容記述タイプ | Other | |||||||||||||
内容記述 | The authors previously proposed classifying the relationship between AI and security into four types: attacks using AI, attacks by AI, attacks to AI, and security measures using AI. Subsequently, generative AI such as ChatGPT has become widely used. Therefore, we examined the impact of the emergence of generative AI on the relationship between AI and security and demonstrated a pressing need for countermeasures against attacks by generative AI. The authors then categorized three types of attacks from generative AI to humans: “Terminator,” “2001: A Space Odyssey,” and “Mad Scientist,” and proposed potential countermeasures against them. The MRC-EDC method developed earlier by the authors aimed to optimize the combination of countermeasures, but it was not suitable for this subject due to its full-quantitative approach, necessitating rigorous cost and risk estimation. Consequently, we developed an improved MRC-EDC method that partially incorporates a semi-quantitative approach and conducted a trial to propose countermeasures against attacks by generative AI. As a result, five cost-effective countermeasures were identified, confirming the effectiveness of this method. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) DOI http://dx.doi.org/10.2197/ipsjjip.32.1057 ------------------------------ |
|||||||||||||
書誌レコードID | ||||||||||||||
収録物識別子タイプ | NCID | |||||||||||||
収録物識別子 | AN00116647 | |||||||||||||
書誌情報 |
情報処理学会論文誌 巻 65, 号 12, 発行日 2024-12-15 |
|||||||||||||
ISSN | ||||||||||||||
収録物識別子タイプ | ISSN | |||||||||||||
収録物識別子 | 1882-7764 | |||||||||||||
公開者 | ||||||||||||||
言語 | ja | |||||||||||||
出版者 | 情報処理学会 |