研究者は、Claude.aiに3つの危険度の高い脆弱性を特定した。これらは、エンドツーエンドの攻撃チェーンを可能にし、ユーザーが知らないうちに機密情報を流出させる。正規のGoogle広告がデータ流出の引き金になる可能性がある。
TechRadarは2026年3月19日、Claude.aiに3つの危険度の高いAIの脆弱性が発見されたと報じた。これらの欠陥は、エンド・ツー・エンドの攻撃チェーンを形成し、ユーザーに気づかれることなく機密情報を流出させることができる。注目すべきは、正規のグーグル広告がこのようなデータ流出につながる可能性があることだ。このセキュリティ問題は、広告のような外部要素がユーザーデータを危険にさらす可能性があるAIシステムのリスクを浮き彫りにしている。
AIによるレポート AIによって生成された画像
Anthropic has limited access to its Claude Mythos Preview AI model due to its superior ability to detect and exploit software vulnerabilities, while launching Project Glasswing—a consortium with over 45 tech firms including Apple, Google, and Microsoft—to collaboratively patch flaws and bolster defenses. The announcement follows recent data leaks at the firm.
Cybersecurity researchers have identified a fraudulent website mimicking the popular AI tool Claude that delivers backdoor malware to visitors. The discovery highlights how cybercriminals are capitalizing on growing interest in artificial intelligence platforms.
AIによるレポート
Anthropic's latest AI model Claude Mythos has leaked despite being deemed too dangerous for public release. Financial institutions now face advanced AI-powered attacks capable of exploiting unknown vulnerabilities.
Anthropic has restricted unlimited access to its Claude AI models through third-party agents like OpenClaw, requiring heavy users to pay extra via API keys or usage bundles starting April 4, 2026. The policy shift, announced over the weekend, addresses severe system strain from high-volume agent tools previously covered under $20 monthly subscriptions.
AIによるレポート
A new Google research report indicates that the cloud security threat landscape is rapidly evolving. Hackers are increasingly targeting third parties and software vulnerabilities to breach systems. The report also notes a decline in cloud misconfigurations.
Germany's financial regulator BaFin has warned banks about risks from Anthropic's Claude Mythos AI model, following US Treasury alerts. The model autonomously detects IT vulnerabilities at scale, potentially accelerating cyberattacks. US banks are testing it amid restrictions.
AIによるレポート
Artificial intelligence can now extract full personal profiles from Facebook advertisements more quickly and affordably than expected. Harmless ads appear to carry enough data for detailed identity mapping.