This talk highlights the security challenges facing AI systems, showing how the rise of generative AI has accelerated and refined cyberattacks such as phishing, deepfakes, malware creation, and DDoS attacks. It also describes how attackers are directly targeting AI itself through techniques like adversarial examples, model extraction, data poisoning, and backdoor attacks. In response, institutions in countries such as the United States and Japan are working to strengthen AI safety. I emphasize that, as AI has become indispensable for both offense and defense, international collaboration and ongoing research and development are essential to ensuring its trustworthiness.
自己紹介
2
高橋健志
•Tampere工科大学、 Roland Berger等を経て、2009年からNICTに勤務
•以来、サイバーセキュリティに関する研究開発に従事
•2017年より、特に AI x サイバーセキュリティの研究開発に従事
•2019年度、University of California, Santa Barbara訪問研究員
•2021年度、内閣府出向
•現在は、同機構内サイバーセキュリティ研究所シニアマネージャ
•ACM Digital Threats: Research and PracticeおよびIEEE Transactions on Reliabilities編集委員
•IETFおよびITU-T SG17にも参画してきたが、直近では業務の都合上、少しご無沙汰
AIによるサイバーチャレンジ: DARPA: AI x CC
9
Cyber Grand Challenge(2016)
✓優勝賞金200万ドル(約3億円)
✓全ての攻防戦がコンピュータにより自動で実施さ
れ、ヒトは見ているのみ
✓自動で脆弱性を発見、パッチ作成、対処
✓CMUのシステム 『Mayhem』が優勝
AI x CC: AI Cyber Challenge(2024-2025)
✓ソフトウェアの脆弱性を自動的に発見・修正し、サ
イバー攻撃から重要インフラを守る競技
✓AIとサイバーセキュリティの統合にるイノベーショ
ンの推進が目的
✓準決勝:Black Hat 2024
✓決勝:Black Hat 2025
AIの安全性強化に向けた、日本の状況
10
•Japan AI Safety Institute (J-AISI) は、2024年2月にIPA内に設立された
–イギリスおよびアメリカにおける AISI設立を受けて設立
–安全、安心で信頼できるAIの実現に向けて、AIの安全性に関する評価手法や基準の検討・推進を実施
–J-AISIは、各種の組織とパートナーシップを構築 して、その目的を達成
•GPAI東京専門家支援センターは、 2024年7月にNICT内に設立
–パリとモントリオールに続いて設立
–AIに関するグローバルなパートナーシップを主導
–SAFEプロジェクト(GPAIの、生成AIの商用化時の安全性を保証する実践的なアプローチの展開を支援する取
組)の支援を中核業務とする
ChatGPT: “Please list up cyber attacks using AI techniques.”
19
Cyberattacks that utilize artificial intelligence (AI) techniques are becoming increasingly sophisticated and challenging to detect. These
AI-driven attacks leverage machine learning, neural networks, and other AI technologies to improve their efficiency and effectiveness.
Here is a list of some common cyberattacks that use AI techniques:
•Phishing Attacks: AI can be used to generate highly convincing phishing emails by analyzing the victim's online presence and
crafting personalized messages that are more likely to be clicked on.
•Spear Phishing: Similar to phishing attacks but highly targeted, spear phishing uses AI to analyze a victim's behavior, preferences,
and social connections to create convincing emails and messages.
•Malware and Ransomware: AI can enhance malware and ransomware attacks by making them more polymorphic and capable of
evading traditional security measures. It can also help attackers choose the right moment to deploy their malware.
•Adversarial Machine Learning: Attackers can use AI to create adversarial examples that can fool machine learning models. For
example, they can manipulate images or data to bypass security measures based on AI.
•Automated Vulnerability Scanning: AI-driven bots can scan for vulnerabilities in networks and systems at a much faster rate than
humans, making it easier for attackers to identify and exploit weaknesses.
•AI-Enhanced DDoS Attacks: AI can be used to amplify distributed denial of service (DDoS) attacks by dynamically adjusting the
attack patterns to maximize disruption.
•Credential Stuffing: AI can automate the process of trying stolen username and password combinations across multiple sites,
increasing the chances of success.
•Deepfakes: AI-generated deepfake videos and audio can be used to impersonate individuals, causing reputational harm or
facilitating social engineering attacks.
ChatGPT: “Please list up cyber attacks using AI techniques.”
20
(continued)
•AI-Generated Text Attacks: AI can generate convincing fake reviews, comments, or news articles to spread disinformation or
manipulate public opinion.
•AI-Powered Bots for Social Engineering: AI-driven chatbots and social engineering tools can mimic human behavior, making it easier
to manipulate people into revealing sensitive information or taking malicious actions.
•Fraud Detection Evasion: AI can be used to develop fraud evasion techniques that adapt to changes in fraud detection systems,
making it harder for businesses to identify fraudulent activities.
•Automated Password Cracking: AI-driven password cracking tools can significantly speed up the process of trying to guess or crack
passwords.
•AI-Enhanced Zero-Day Attacks: AI can help identify and exploit zero-day vulnerabilities faster, potentially before security patches are
available.
•AI-Generated Network Traffic: Attackers can use AI to generate legitimate-looking network traffic to blend in with normal activities,
making it more challenging to detect malicious activity.
•Behavioral Biometric Spoofing: AI can generate synthetic biometric data (such as fingerprints or facial features) to impersonate
individuals for authentication purposes.
These are just a few examples of how AI is being used to enhance cyberattacks. As AI technology continues to advance, it's crucial for
organizations to develop robust cybersecurity strategies and defenses to counter these evolving threats.
モデル摂取
27
出展:https://www.mbsd.jp/aisec_portal/attack_copycat_cnn.html#copycat_cnn
•攻撃者は標的 AI(学習済みCNN)に複数のデータ(画像)を入力し、 AIの分類結果(ラベル)を入力デー
タに紐付けることで「模倣データセット」を作成
•次に、攻撃者は模倣データセットを使用して手元にある独自の AI を学習させ、ターゲット AI と同等の
パフォーマンスを持つ「コピーキャット ネットワーク」を構築
c
ポイズニング攻撃 : Error-specific poisoning
28
出展: https://jpsec.ai/attack-to-hijack-ai/, https://doi.org/10.6028/NIST.AI.100-2e2023.ipd
※It is classified into “ship” though it should be classified into “frog”
標的AI に入力された特定のデータを、攻撃者が意図したクラスに分類する攻撃
•攻撃者のみが、その特定のデータ (トリガーと呼ぶ )を知っている
•注入データは、 triggerに分類される敵対的サンプル
d
ポイズニング攻撃 : Error-generic poisoning
29
出展: https://jpsec.ai/attack-to-hijack-ai/, https://doi.org/10.6028/NIST.AI.100-2e2023.ipd
※The decision boundary is distorted and
misclassifications occur frequently.
できるだけ多くの誤分類を誘発することを目的とした攻撃
⚫分類先のクラスにかかわらず、より多くの誤分類を誘発
⚫すなわち、AIの推測制度が大幅に低下
⚫注入データは任意のクラスに分類される敵対的サンプル
d