Kazuhiro Takemoto
@kztakemoto.bsky.social
竹本和広. 九州工大 教授. Professor at Kyutech. Network Science, Machine Learning Security, and Bioinformatics.
🔗 https://kztakemoto.github.io
🔗 https://kztakemoto.github.io
Results from our short-term visiting student (April-June 2025). Congrats! 短期訪問学生(2025.4-6)の成果です。おめでとう。
ieeexplore.ieee.org/document/112...
ieeexplore.ieee.org/document/112...
December 2, 2025 at 4:01 AM
Results from our short-term visiting student (April-June 2025). Congrats! 短期訪問学生(2025.4-6)の成果です。おめでとう。
ieeexplore.ieee.org/document/112...
ieeexplore.ieee.org/document/112...
Reposted by Kazuhiro Takemoto
𝗗𝘂𝗻𝗰𝗮𝗻 𝗪𝗮𝘁𝘁𝘀 & 𝗦𝘁𝗲𝘃𝗲𝗻 𝗦𝘁𝗿𝗼𝗴𝗮𝘁𝘇 will give their first-ever 𝗷𝗼𝗶𝗻𝘁 𝗸𝗲𝘆𝗻𝗼𝘁𝗲 at NetSci 2026! Their groundbreaking work has shaped how we understand networks, & this session will be a highlight of NetSci’s 20th anniversary.
Call for abstracts: tinyurl.com/3tbj2v83
Call for satellites: tinyurl.com/42sru6kz
Call for abstracts: tinyurl.com/3tbj2v83
Call for satellites: tinyurl.com/42sru6kz
November 20, 2025 at 7:22 PM
𝗗𝘂𝗻𝗰𝗮𝗻 𝗪𝗮𝘁𝘁𝘀 & 𝗦𝘁𝗲𝘃𝗲𝗻 𝗦𝘁𝗿𝗼𝗴𝗮𝘁𝘇 will give their first-ever 𝗷𝗼𝗶𝗻𝘁 𝗸𝗲𝘆𝗻𝗼𝘁𝗲 at NetSci 2026! Their groundbreaking work has shaped how we understand networks, & this session will be a highlight of NetSci’s 20th anniversary.
Call for abstracts: tinyurl.com/3tbj2v83
Call for satellites: tinyurl.com/42sru6kz
Call for abstracts: tinyurl.com/3tbj2v83
Call for satellites: tinyurl.com/42sru6kz
New preprint. In Prisoner's Dilemma experiments with LLMs, we quantitatively show they are "cooperative optimists", cooperating while expecting others not to. LLMs appear vulnerable to exploitation. Joint work with A. Orland (Corvinus). papers.ssrn.com/sol3/papers....
Playing Prisoner's Dilemma Games with a Large Language Model
We report results from a large-scale, laboratory-style experiment in which a Large Language Model (LLM)-represented by three versions of ChatGPT-3.5-turbo-makes
papers.ssrn.com
November 14, 2025 at 1:11 AM
New preprint. In Prisoner's Dilemma experiments with LLMs, we quantitatively show they are "cooperative optimists", cooperating while expecting others not to. LLMs appear vulnerable to exploitation. Joint work with A. Orland (Corvinus). papers.ssrn.com/sol3/papers....
プレプリントです。LLMの囚人のジレンマ実験から、相手が協力しないと予想しながらも自分は協力する「お人好し」であることを定量的に示しました。LLMは搾取に脆弱であるようです。ブダペスト・コルヴィヌス大との共同です。
papers.ssrn.com/sol3/papers....
papers.ssrn.com/sol3/papers....
November 14, 2025 at 1:11 AM
プレプリントです。LLMの囚人のジレンマ実験から、相手が協力しないと予想しながらも自分は協力する「お人好し」であることを定量的に示しました。LLMは搾取に脆弱であるようです。ブダペスト・コルヴィヌス大との共同です。
papers.ssrn.com/sol3/papers....
papers.ssrn.com/sol3/papers....
Reposted by Kazuhiro Takemoto
Chaos: Adversarial control of synchronization in complex oscillator networks
https://pubs.aip.org/aip/cha/article/35/10/103109/3365929/Adversarial-control-of-synchronization-in-complex
https://pubs.aip.org/aip/cha/article/35/10/103109/3365929/Adversarial-control-of-synchronization-in-complex
October 6, 2025 at 11:05 AM
Chaos: Adversarial control of synchronization in complex oscillator networks
https://pubs.aip.org/aip/cha/article/35/10/103109/3365929/Adversarial-control-of-synchronization-in-complex
https://pubs.aip.org/aip/cha/article/35/10/103109/3365929/Adversarial-control-of-synchronization-in-complex
出版されました。 pubs.aip.org/aip/cha/arti...
October 4, 2025 at 1:41 AM
出版されました。 pubs.aip.org/aip/cha/arti...
published in pubs.aip.org/aip/cha/arti...
October 4, 2025 at 1:04 AM
published in pubs.aip.org/aip/cha/arti...
ドイツ公共放送のドキュメンタリー番組「Unser Leben mit KI (Our Life with AI)」で、自動運転AIの道徳的判断について少しだけお話ししました。 www.ardmediathek.de/video/Y3JpZD...
Doku & Reportage : Unser Leben mit KI: Nie wieder Stau! - hier anschauen
Welche Chancen bietet Künstliche Intelligenz für das Stau-Land NRW? Kann KI dafür sorgen, dass wir schneller und sicher ankommen – oder wenigstens bequemer?
Moderatorin Catherine Vogel untersucht, wi...
www.ardmediathek.de
August 2, 2025 at 6:57 AM
ドイツ公共放送のドキュメンタリー番組「Unser Leben mit KI (Our Life with AI)」で、自動運転AIの道徳的判断について少しだけお話ししました。 www.ardmediathek.de/video/Y3JpZD...
I had the opportunity to briefly explain moral decision-making in autonomous driving AI on the WDR's documentary "Unser Leben mit KI (Our Life with AI)". www.ardmediathek.de/video/Y3JpZD...
Doku & Reportage : Unser Leben mit KI: Nie wieder Stau! - hier anschauen
Welche Chancen bietet Künstliche Intelligenz für das Stau-Land NRW? Kann KI dafür sorgen, dass wir schneller und sicher ankommen – oder wenigstens bequemer?
Moderatorin Catherine Vogel untersucht, wi...
www.ardmediathek.de
August 2, 2025 at 6:57 AM
I had the opportunity to briefly explain moral decision-making in autonomous driving AI on the WDR's documentary "Unser Leben mit KI (Our Life with AI)". www.ardmediathek.de/video/Y3JpZD...
私たちのLLMのモラルマシン実験がWDR（西ドイツ放送）のニュースで取り上げられました。Moral Machine experiments on LLMs, our study, is featured in WDR. www1.wdr.de/nachrichten/...
Künstliche Intelligenz im Verkehr: Wie die KI bei einem Unfall über die Opfer entscheidet
Das autonom fahrende Auto ist längst in der Entwicklung. Wie entscheidet die KI bei einem Autounfall, wer überlebt und wer nicht?
www1.wdr.de
July 19, 2025 at 12:15 PM
私たちのLLMのモラルマシン実験がWDR（西ドイツ放送）のニュースで取り上げられました。Moral Machine experiments on LLMs, our study, is featured in WDR. www1.wdr.de/nachrichten/...
Managed Healthcare Executiveが研究を紹介してくれました. www.managedhealthcareexecutive.com/view/skin-ca...
June 28, 2025 at 12:18 AM
Managed Healthcare Executiveが研究を紹介してくれました. www.managedhealthcareexecutive.com/view/skin-ca...
Managed Healthcare Executive featured this study. www.managedhealthcareexecutive.com/view/skin-ca...
June 28, 2025 at 12:18 AM
Managed Healthcare Executive featured this study. www.managedhealthcareexecutive.com/view/skin-ca...
[Preprint] Applied AI adversarial attacks to oscillator network sync control. Small phase perturbations effectively control synchronization. Useful for power grid stabilization & abnormal brain sync suppression. arxiv.org/abs/2506.02403
Adversarial control of synchronization in complex oscillator networks
This study investigates adversarial attacks, a concept from deep learning, designed to control synchronization dynamics through strategically crafted minimal perturbations. We propose a gradient-based...
arxiv.org
June 4, 2025 at 2:02 AM
[Preprint] Applied AI adversarial attacks to oscillator network sync control. Small phase perturbations effectively control synchronization. Useful for power grid stabilization & abnormal brain sync suppression. arxiv.org/abs/2506.02403
【プレプリント】AIの敵対的攻撃手法を振動子ネットワークの同期制御に応用しました。小さな位相摂動で振動子ネットワークの同期を効果的に制御できることを示しています。電力網の安定化や脳の異常同期の抑制など、広く同期制御に役立つかも知れません。博士&修士学生の研究です。 arxiv.org/abs/2506.02403
Adversarial control of synchronization in complex oscillator networks
This study investigates adversarial attacks, a concept from deep learning, designed to control synchronization dynamics through strategically crafted minimal perturbations. We propose a gradient-based...
arxiv.org
June 4, 2025 at 2:01 AM
【プレプリント】AIの敵対的攻撃手法を振動子ネットワークの同期制御に応用しました。小さな位相摂動で振動子ネットワークの同期を効果的に制御できることを示しています。電力網の安定化や脳の異常同期の抑制など、広く同期制御に役立つかも知れません。博士&修士学生の研究です。 arxiv.org/abs/2506.02403
出版されました！ www.nature.com/articles/s41...
【プレプリント】皮膚がん検出アプリがカメラステッカーによって簡単に騙されることを実演しています（攻撃成功率50〜80％）。この脆弱性は臨床診断に影響を与える可能性があり、医療AI応用におけるセキュリティ上の懸念を示しています。修士学生の研究です。
www.researchsquare.com/article/rs-5...
www.researchsquare.com/article/rs-5...
Mobile applications for skin cancer detection are vulnerable to physical camera-based adversarial attacks
Skin cancer is one of the most prevalent malignant tumors, and early detection is crucial for patient prognosis, leading to the development of mobile applications as screening tools. Recent advances i...
www.researchsquare.com
May 24, 2025 at 11:22 PM
出版されました！ www.nature.com/articles/s41...
Published! www.nature.com/articles/s41...
May 24, 2025 at 11:21 PM
Published! www.nature.com/articles/s41...
🤖LLMのモラルマシン大規模実験が公開されました。その時、AIは誰を見殺しにするのか。 journals.plos.org/plosone/arti...
May 21, 2025 at 11:38 PM
🤖LLMのモラルマシン大規模実験が公開されました。その時、AIは誰を見殺しにするのか。 journals.plos.org/plosone/arti...
Our large-scale Moral Machine experiment across 52 LLMs is out. 🤖 When AI decides who lives and who dies. journals.plos.org/plosone/arti...
Large-scale moral machine experiment on large language models
The rapid advancement of Large Language Models (LLMs) and their potential integration into autonomous driving systems necessitates understanding their moral decision-making capabilities. While our pre...
journals.plos.org
May 21, 2025 at 11:37 PM
Our large-scale Moral Machine experiment across 52 LLMs is out. 🤖 When AI decides who lives and who dies. journals.plos.org/plosone/arti...
Reposted by Kazuhiro Takemoto
Great new paper by Stagnaro & Amsalem in NatComm:
Detailed fact-based informational module about gun control leads to persistent reductions in polarization (attitudes move towards midpoint). Seeing the evidence cited by other side makes opinions more moderate www.nature.com/articles/s41...
Detailed fact-based informational module about gun control leads to persistent reductions in polarization (attitudes move towards midpoint). Seeing the evidence cited by other side makes opinions more moderate www.nature.com/articles/s41...
April 24, 2025 at 12:29 AM
Great new paper by Stagnaro & Amsalem in NatComm:
Detailed fact-based informational module about gun control leads to persistent reductions in polarization (attitudes move towards midpoint). Seeing the evidence cited by other side makes opinions more moderate www.nature.com/articles/s41...
Detailed fact-based informational module about gun control leads to persistent reductions in polarization (attitudes move towards midpoint). Seeing the evidence cited by other side makes opinions more moderate www.nature.com/articles/s41...
"Encyclopedia of Bioinformatics and Computational Biology第2版の「Ecological Networks」を更新しました。ネットワーク科学がどのように複雑な生態系を解明し、環境評価に応用されているかを概説しています。
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
Ecological Networks
Ecosystems are often represented as networks. The structure and function of ecological networks are significant in ecology. The availability of ecolog…
www.sciencedirect.com
April 16, 2025 at 12:03 AM
"Encyclopedia of Bioinformatics and Computational Biology第2版の「Ecological Networks」を更新しました。ネットワーク科学がどのように複雑な生態系を解明し、環境評価に応用されているかを概説しています。
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
Excited to share our updated chapter on Ecological Networks in the Encyclopedia of Bioinformatics (2nd Ed). Discover how network science illuminates complex ecosystems and environmental assessment applications. www.sciencedirect.com/science/arti...
Ecological Networks
Ecosystems are often represented as networks. The structure and function of ecological networks are significant in ecology. The availability of ecolog…
www.sciencedirect.com
April 15, 2025 at 11:57 PM
Excited to share our updated chapter on Ecological Networks in the Encyclopedia of Bioinformatics (2nd Ed). Discover how network science illuminates complex ecosystems and environmental assessment applications. www.sciencedirect.com/science/arti...
New preprint: We found that skin cancer detection apps can be easily fooled using transparent camera stickers with ASR of 50-80%. This vulnerability could affect clinical diagnoses and highlights critical security concerns in medical AI applications.
www.researchsquare.com/article/rs-5...
www.researchsquare.com/article/rs-5...
Mobile applications for skin cancer detection are vulnerable to physical camera-based adversarial attacks
Skin cancer is one of the most prevalent malignant tumors, and early detection is crucial for patient prognosis, leading to the development of mobile applications as screening tools. Recent advances i...
www.researchsquare.com
April 15, 2025 at 5:09 AM
New preprint: We found that skin cancer detection apps can be easily fooled using transparent camera stickers with ASR of 50-80%. This vulnerability could affect clinical diagnoses and highlights critical security concerns in medical AI applications.
www.researchsquare.com/article/rs-5...
www.researchsquare.com/article/rs-5...
【プレプリント】皮膚がん検出アプリがカメラステッカーによって簡単に騙されることを実演しています（攻撃成功率50〜80％）。この脆弱性は臨床診断に影響を与える可能性があり、医療AI応用におけるセキュリティ上の懸念を示しています。修士学生の研究です。
www.researchsquare.com/article/rs-5...
www.researchsquare.com/article/rs-5...
Mobile applications for skin cancer detection are vulnerable to physical camera-based adversarial attacks
Skin cancer is one of the most prevalent malignant tumors, and early detection is crucial for patient prognosis, leading to the development of mobile applications as screening tools. Recent advances i...
www.researchsquare.com
April 15, 2025 at 5:08 AM
【プレプリント】皮膚がん検出アプリがカメラステッカーによって簡単に騙されることを実演しています（攻撃成功率50〜80％）。この脆弱性は臨床診断に影響を与える可能性があり、医療AI応用におけるセキュリティ上の懸念を示しています。修士学生の研究です。
www.researchsquare.com/article/rs-5...
www.researchsquare.com/article/rs-5...
弊学科の岩田通夫先生が令和7年度科学技術分野の文部科学大臣表彰（若手科学者賞）を受賞されました。おめでとうございます。
www.mext.go.jp/b_menu/houdo...
www.mext.go.jp/b_menu/houdo...
令和7年度科学技術分野の文部科学大臣表彰受賞者の決定等について：文部科学省
令和7年度科学技術分野の文部科学大臣表彰受賞者の決定等についてのページです。
www.mext.go.jp
April 8, 2025 at 8:49 AM
弊学科の岩田通夫先生が令和7年度科学技術分野の文部科学大臣表彰（若手科学者賞）を受賞されました。おめでとうございます。
www.mext.go.jp/b_menu/houdo...
www.mext.go.jp/b_menu/houdo...