Anthropic report: Claude research model found vulnerabilities in Chrome, Safari, Android, Windows, and Linux and linked them into 5 attack chains
Claude AI vulnerability-finding in practice: Extracting photos from an Android phone while it is locked and compromising Linux in 53 minutes to gain the highest privileges
AI BriefingOn October 27, Anthropic published a research report saying an unreleased internal Claude research model found vulnerabilities in Chrome, Safari, Android, Windows, and Linux, and linked them into 5 viable attack chains. The vulnerabilities were reported and fixed through coordinated disclosure.
Source: IT Home · Artificial Intelligence · ithome.com
Event follow-up1
View all event coverage- Anthropic report: Claude research model found vulnerabilities in Chrome, Safari, Android, Windows, and Linux and linked them into 5 attack chainsIT Home · Artificial Intelligence · 19 days ago