Beyond AI Logo



【プレスリリース】脳のゆらぎを取り入れてAIを安全にする ――深層ニューラルネットワークの隠れ層にゆらぎを導入し脆弱性を軽減―― [Press Release] Making AI secure by introducing random noise that mimics brain neurons ――Reduces its vulnerability against some adversarial examples by injecting random noise in the hidden layers of deep neural networks――

東京大学大学院医学系研究科 機能生物学専攻 統合生理学分野の大木研一教授と浮田純平大学院生(研究当時)の研究チームは、深層ニューラルネットワークに脳の神経細胞を模したゆらぎを導入することで、深層ニューラルネットワークが持つ脆弱性の一部が軽減できることを明らかにしました。


本研究は、Beyond AI 研究推進機構、日本医療研究開発機構(AMED)「革新的技術による脳機能ネットワークの全容解明プロジェクト」、文部科学省科学研究費助成事業、CREST-JSTなどの支援を受けて行われました。

本研究の成果はNeural Networks誌(9月16日オンライン版)に掲載されました。


・掲載論文 (Title: Adversarial attacks and defenses using feature-space stochasticity)
DOI 10.1016/j.neunet.2023.08.022

・東京大学ホームページ(UTokyo Focus)

A research team consisting of Professor Kenichi OHKI and Jumpei UKITA (a graduate student at the time of the research) of the Department of Physiology, Division of Functional Biology, Graduate School of Medicine, the University of Tokyo, revealed that some of the vulnerabilities in deep neural networks can be mitigated by injecting random noise that mimics the brain in deep neural networks.

Currently, artificial intelligence (AI) is evolving at an accelerating pace, and its underlying structure is based on deep neural networks. Deep neural networks are known to be tricked into producing outputs that are clearly different from that of humans by malicious attacks, known as adversarial attacks. For example, image recognition AI in self-driving cars must correctly recognize a "stop" road sign as "stop" to make the car stop. However, the image recognition AI may not be able to correctly recognize a "stop" road sign generated by a hostile attack, even if it is clearly a "stop" sign when seen by a human. As a result, the car may not be able to stop, leading to a traffic accident. Thus, vulnerability to hostile attacks is one of the major challenges of implementing AI in society.

Incorporating brain properties of animals, such as humans, into AI may help overcome such vulnerabilities. The research team discovered that certain types of vulnerability can be reduced by introducing noise that mimics the randomness of neurons in the brain into deep neural networks. By using this method, the possibility of creating AI that more closely resembles the behavior of humans and other animals is thought to be greater.

This research was supported by the Institute for AI and Beyond of the University of Tokyo, the Japan Agency for Medical Research and Development (AMED) "Project to Elucidate the Entire Functional Brain Network through Innovative Technology", the Grant-in-Aid for Scientific Research from the Ministry of Education, Culture, Sports, Science and Technology, and CREST-JST.
The research result was published in Neural Networks on 16 September 2023 online.

Professor Ohki is the Project Leader for the Basic Research Project entitled “Development of next generation AI by modeling brain information” at the Institute for AI and Beyond.

・The full press release (in Japanese only) in PDF.

・Published paper (Title: Adversarial attacks and defenses using feature-space stochasticity)
DOI 10.1016/j.neunet.2023.08.022

・Article in English at UTokyo Focus

第2回GENEEシンポジウム「生成AIのもたらす社会課題 ー データバイアス・フェイクニュース・揺さぶられる法制度」にB’AI グローバル・フォーラムの板津リーダーらが登壇 Profs. Yuko Itatsu, Kaori Hayashi, Tohko Tanaka of the B'AI Global Forum spoke at the 2nd GENEE Symposium titled “Social Challenges Brought by Generative AI: Data Bias, Fake News, and Disordered Legal Systems”

東京大学 エドテック連携研究機構 生成AIと教育環境研究プロジェクト(GENEE)主催、B’AI Global Forum共催のイベント、第2回GENEEシンポジウム「生成AIのもたらす社会課題―データバイアス・フェイクニュース・揺さぶられる法制度」が2023年8月3日に開催され、B’AI Global Forumから、板津木綿子教授、林香里教授、田中東子教授が登壇しました。


The 2nd GENEE Symposium titled “Social Challenges Brought by Generative AI: Data Bias, Fake News, and Disordered Legal Systems” was held on August 3, 2023. The event was hosted by Generative AI and Educational Environment Research Project (GENEE) of the Collaborative Research Organization of Educational Technology at the University of Tokyo and co-hosted by the B’AI Global Forum.
Profs. Kaori Hayashi, Tohko Tanaka, and Yuko Itatsu of the B'AI Global Forum were among the speakers at the symposium.

For further details ;

【プレスリリース】 自閉スペクトラム症の知覚を体験することで ネガティブな感情が改善される [Press Release] Reduce the stigma of autism spectrum disorders by incorporating the experience of simulated autistic perception

元中長期研究「AI×発達障害当事者研究:計算論的神経科学による認知個性の顕在化」(AIと社会)のリーダーで、現在はBeyond AI 研究推進機構のアラムナイ委員である長井志江特任教授(東京大学国際高等研究所ニューロインテリジェンス国際研究機構(IRCN))が主任研究者として研究に関わる自閉スペクトラム症(ASD)知覚体験シミュレータを使った同症に関する新たな知見について、8月3日に記者発表が出されました。


自閉スペクトラム症(ASD)知覚体験シミュレータについては、長井先生が昨年10月に出演した「第8回 Beyond AI サイエンスカフェ」動画の中でも紹介されています。

A press release was issued on August 3, 2023 regarding new findings on a study on autism spectrum disorder (ASD) using the ASD perceptual experience simulator, in which Project Professor Yukie Nagai of the International Research Center for Neurointelligence (IRCN) at the University of Tokyo was involved as the principle investigator.

Professor Nagai was the former leader of the Mid- and Long-term Research Project “AI x Tojisha-Kenkyu: Computational Neuroscience for Systematic Understanding of Cognitive Individuality” and current Alumni committee member of the Institute for AI and Beyond.

Full press release at the IRCN official website:

Professor Nagai presented the ASD perception experience simulator in the 8th Beyond AI Science Café video, in which she was featured last year.
The video, which is available in Japanese at the Institute for AI and Beyond YouTube Channel as linked below;

[受賞] 伊藤信貴特任講師と杉山将教授との論文が、ICASSP2023においてベストペーパーアワードを受賞 [Award] Dr. Nobutaka ITO (Project Lecturer) and Professor Masashi SUGIYAMA won the Best Paper Award at ICASSP 2023

大学院新領域創成科学研究科の伊藤信貴特任講師と杉山将教授の論文「Audio Signal Enhancement with Learning from Positive and Unlabeled Data」が、2023年6月4日-10日にギリシャで開催されたICASSP 2023(2023 IEEE International Conference on Acoustics, Speech and Signal Processing)において、6127編の投稿論文(内、2765編が採録)の中からベストペーパーアワードに選出されました。
6月9日、現地ギリシャのロードス島にて開かれた授賞式に参加した伊藤特任講師が、組織委員会Petros Maragosゼネラルチェアらから賞状を授与されました。

杉山教授と伊藤特任講師は、Beyond AI 研究推進機構の基礎研究プロジェクト「限られた教師情報からの高精度な予測モデルの自動構築に関する研究(研究リーダー:原田達也教授)」において、それぞれサブリーダー、研究担当者を務めています。

A scientific paper entitled “Audio Signal Enhancement with Learning from Positive and Unlabeled Data” written by Dr. Nobutaka ITO and Professor Masashi SUGIYAMA of the Graduate School of Frontier Science at the University of Tokyo was selected for the “Best Paper Award” at 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023), one of the largest and most influential research conferences of the Signal Processing Society in the world. The paper was selected from 6127 submitted papers, of which 2765 were accepted for publication in the conference proceedings.

Dr. Ito who participated in-person in the conference, received the award at the awards ceremony held on Friday, June 9, in Rhodes, Greece from the organizing committee, represented by General Chair Dr. Petros Maragos.

Professor Sugiyama and Dr. Ito are respectively, the project sub-leader and associate researcher of the Basic research project (Advancement of Fundamental AI) titled “Automatic Learning of High Accurate Prediction Models from Limited Supervised Data” led by Professor Tatsuya HARADA (Research Center for Advanced Science and Technology, The University of Tokyo) in the Institute for AI and Beyond.

<授賞式にて組織委員会のPetros Maragosゼネラルチェアらから祝福される伊藤特任講師>

Dr. Ito receiving the honorable certificate from Petros Maragos General Chair

・ICASSP2023 オフィシャルサイト

【プレスリリース】ダークマターを見る!– HSC国際チームが宇宙の標準理論を検証 [Press Release] How to see the invisible: Using dark matter distribution to test our cosmological model

東京大学 国際高等研究所 カブリ数物連携宇宙研究機構(Kavli IPMU)/ Beyond AI 研究推進機構の高田昌弘 教授と杉山素直 特任研究員(研究プロジェクト:量子ゆらぎから天の川銀河の形成史の解明を通じたAIの進展 / 研究リーダー: 村山斉 教授)を含む、すばる望遠鏡の超広視野主焦点カメラによる大規模撮像探査(HSC-SSP)の国際共同研究チームから、アインシュタインが提案した宇宙の標準理論の矛盾を突く可能性のある研究成果が発表されました。

「今回、すばる望遠鏡Hyper Suprime-Cam宇宙観測の中間データを用いて、弱重力レンズ効果という宇宙の現象を測定し、その測定結果と宇宙理論を比較することで、宇宙論パラメータとよばれる宇宙を記述する物理量を測定しました。この理論モデルのなかで、宇宙論シミュレーションの大量のデータを学習データとして用い、ディープラーニングで回帰モデルを構築しました。つまり、この理論モデルはスーパーコンピュータで作った宇宙と同等で、すばるの観測とスパコンの理論を比較したことと同等になります。それを用いて、宇宙論パラメータを測定したところ、初期宇宙のデータとの矛盾が発見されました」


An international team of astrophysicists and cosmologists from various institutes, including Professor Masahiro Takada and Dr. Sunao Sugiyama, a Project Researcher, of the Kavli Institute for the Physics and Mathematics of the Universe (Kavli IPMU) at the University of Tokyo, submitted a set of five papers that suggest the possibility that the standard cosmological model proposed by Einstein may be incomplete in some interesting way.

Professor Takada commented on the application of AI to the experiment as follows:
“In this study, we used interim data from the Subaru Telescope Hyper Suprime-Cam survey to measure a cosmological phenomenon called weak gravitational lensing effect. We then compared the measurement results with the cosmological model to measure physical quantities that describe the universe, called cosmological parameters.
In this theoretical model, we constructed a regression model using deep learning, with a large amount of data from cosmological simulations as training data. In other words, the theoretical model is equivalent to a universe created on a supercomputer and is equivalent to comparing Subaru’s observations with a supercomputer’s theory. Using this, we measured the cosmological parameters and found discrepancies with the data of the early universe.”

Professor Takada and Dr. Sugiyama are the Sub-Leader and Associate Researcher, respectively, of the Basic research project “New developments in AI through study of evolution of the Milky Way from initial quantum fluctuations to its assembly” (Research Leader: Professor Hitoshi Murayama of Kavli IPMU) at the Institute for AI and Beyond.

Full press release at the Kavli IPMU Official Website:
Project page of Professor Murayama's Research Group at the Institute for AI and Beyond:

齊藤英治先生の研究グループからコラムがアップされました Professor Eiji Saitoh, leader of the Mid- and Long-term research project has posted a column regarding his research at the Institute for AI and Beyond

中長期研究プロジェクト「AIを活用した物質の量子的性質の解読 (Quantum ID – 物質の
「量子指紋」をAIで読み取り利用する - )」の齊藤英治リーダー(大学院工学系研究科 教授)が
自身のHPにBeyond AI 研究推進機構での研究に関するコラムをアップしました。

タイトル: 機械学習を用いた新たな挑戦:AIと物理は相性が良い?(by 皆川麻利江/研究協力者)


Professor Eiji Saitoh of the Graduate School of Engineering, leader of the Mid- and Long-term research project "Analysis of materials’ quantum properties using AI (Quantum ID: Exploiting “Quantum Fingerprintings” of materials with AI)", has posted a column on his website regarding his research at the Institute for AI and Beyond.
The column is titled “New Challenges with Machine Learning - Are AI and Physics a Good Match?” and written by Marie Minagawa, his research collaborator.

・Link to the column (available in Japanese only):
・Prof. Saitoh’s Research Project page:

【プレスリリース】HL7 FHIR規格による健康・医療データの標準化と データ流通を促進する新会社「HEMILLIONS」を設立 〜安全・安心に健康・医療データを活用できる社会を構築し、 次世代の医療やヘルスケアの実現を目指す〜  【Press Release】HEMILLIONS Inc. established to promote the standardization and dissemination of health and medical data using the HL7 FHIR standard - Aiming to realize the next generation of medicine and healthcare by creating a society where health and medical data are utilized safely and securely -


HEMILLIONSは、Beyond AI 研究推進機構における取り組みからスタートし、技術研究組合(CIP)を経て株式会社化されました。Beyond AI 研究推進機構は、最先端研究とAI(人工知能)との融合によって新たな学術分野の創出を目指すとともに、研究成果の実社会における活用を加速し、教育研究の充実に必要な資源を大学に還元するエコシステムの構築を進めています。HEMILLIONSはBeyond AI 研究推進機構から事業化および株式会社化した第1号であり、また東京大学にとっては知の対価として、事業会社の普通株式を直接保有する初のケースとなります。 Beyond AI 研究推進機構では、今後もエコシステムの構築を進めるべく、CIPの制度などを活用した事業化を進めて参ります。


・東京大学ホームページUTokyo Focus
・ソフトバンク HP

HEMILLIONS Inc., a commercial company, was established on 7th April as a joint initiative of the University of Tokyo, SoftBank Corp., and KIS Inc. The company will promote health and medical data standardization and their dissemination by utilizing the HL7 FHIR (FHIR: Fast Healthcare Interoperability Resources) standard. Ultimately, HEMILLIONS will work towards building a society that can utilize health and medical data safely and securely by developing and providing solutions such as FRUCtoS, a platform software including FHIR server.

The HEMILLIONS started as an applied research project, a part of the efforts undertaken by the Institute for AI and Beyond, and was later converted to a joint venture company through the Collaborative Innovation Partnership (CIP) system. It is the first commercialized and incorporated company initiated by the Institute. It is also the first case for the University of Tokyo to directly hold common shares of a company in return for their intellectual properties.

The Institute of AI and Beyond aims to create new academic fields by integrating fundamental technology research of AI and other research fields. It also aims to establish an ecosystem which can return resources to the University to enhance its education and research activities by accelerating the social implementation and business deployment of the research outcomes generated from the Institute. The Institute will continue its efforts in commercialization based on the research outcomes via the CIP system to further promote the ecosystem.

The full press release is available below (in Japanese only) (PDF).

UTokyo Focus
SoftBank News

板津木綿子リーダーがNHK日曜討論「広がるAI=人工知能 私たちはどう向き合う?」に出演 Yuko Itatsu, Leader of the Basic research project appeared on NHK’s Sunday Debate and participated in a discussion about AI

中長期研究グループ B’AI Global Forum(ビー・エイアイ グローバル・フォーラム) AI時代における真のジェンダー平等社会の実現とマイノリティの権利保障のための規範・倫理・実践研究の板津木綿子リーダー(大学院情報学環・学際学府 教授)が、4月16日に放送されたNHK日曜討論「広がるAI=人工知能 私たちはどう向き合う?」に出演し、急速に進化する人工知能=AIに対し、どう向き合うか、及びChat GPT登場による教育・雇用への影響や、規制・ルール作り等に関する討論に参加しました。


Yuko Itatsu, the leader of the Basic research project “B’AI Global Forum: Research on norms, ethics and praxis for a truly gender equal society and a guarantee of rights for minorities in the AI age”, appeared on NHK’s Sunday Debate, broadcasting on April 16. She participated in the discussion with other specialists on how to deal with rapidly evolving Artificial Intelligence (AI), the impact of the emergence of ChatGPT on education and the workforce, and what regulations and rules should be established.

NHK website (available only in Japanese) :

B’AI グローバル・フォーラムの編著『AIから読み解く社会 ――権力化する最新技術』が刊行されました B’AI Global Forum has published its first book “Understanding AI in Society: How Technology Exerts Power.”

板津木綿子教授(大学院情報学環・学際学府)が率いるB’AI グローバル・フォーラムから、編著『AIから読み解く社会 ――権力化する最新技術』(東京大学出版会、2023年3月)が刊行されました。

板津教授は、中長期研究プロジェクト B’AI Global Forum(ビー・エイアイ グローバル・フォーラム) AI時代における真のジェンダー平等社会の実現とマイノリティの権利保障のための規範・倫理・実践研究においてリーダーを務めています。


B’AI Global Forum ウエブサイト

B’AI Global Forum led by Professor Yuko Itatsu of the Graduate School of Interdisciplinary Information Studies, has published its first book “Understanding AI in Society: How Technology Exerts Power.” (The University of Tokyo Press, March 2023) .

Professor Itatsu is the research leader of the basic research project “B’AI Global Forum: Research on norms, ethics and praxis for a truly gender equal society and a guarantee of rights for minorities in the AI age”.

For further details of the book, please visit the website below (Japanese only).

B’AI Global Forum Official Website

科学雑誌 Nature (2023年3月9日号)にBeyond AI 研究推進機構の記事広告が掲載されました An advertisement article entitled "The surprising new ideas coming from AI” of the Institute for AI and Beyond appeared in the scientific journal Nature on 9 March

国際的な総合科学雑誌 Nature (2023年3月9日号)に、Beyond AI 研究推進機構の記事広告「The surprising new ideas coming from AI」がNature Index Japan特集の一部として掲載されました。
当記事では、Beyond AI 研究推進機構の取組と共に、中長期研究プロジェクトの池内与志穂 生産技術研究所 准教授(人工脳組織を用いた脳機能解明)、齊藤英治 工学系研究科 教授(大AIを活用した物質の量子的性質の解読 (Quantum ID -物質の「量子指紋」をAIで読み取り利用する-)、板津木綿子リーダー 情報学環・学際情報学府 教授(B’AI Global Forum(ビー・エイアイ グローバル・フォーラム) AI時代における真のジェンダー平等社会の実現とマイノリティの権利保障のための規範・倫理・実践研究)の研究が取り上げられています。

特集のトップページ :

An advertisement article entitled “The surprising new ideas coming from AI” about the Institute for AI and Beyond was published in the international scientific journal Nature on 9 March. The article was featured as part of a special issue on Japan by Nature Index. In the article, the efforts of the Institute are covered as well as the studies of Associate Professor Yoshiho IKEUCHI of the Institute of Industrial Science, Professor Eiji SAITOH of the Graduate School of Engineering, and Professor Yuko ITATSU of Graduate School of Interdisciplinary Information Studies are discussed. All three faculty are research leaders of Mid- and Long-term Research Projects at the Institute.

Link to the articles:
Link to the Top page of the special issue of Nature Index:
Nature issued on March 9, 2023