Browsing Tag
AI Security
46 posts
Security risks, defenses, and engineering practices for AI systems and models.
Microsoft MDASH Moves AI Bug Hunting Into Real Security Workflows
Microsoft says its MDASH agentic security system is now being used across Windows, Azure, and identity workflows, with new findings in Hyper-V, HTTP.sys, the Windows kernel, and Active Directory. The update shows AI vulnerability discovery moving from benchmark claims toward real engineering pipelines, while proof generation remains the hard part.
Security Leaders Say the Fable 5 Ban Could Hurt Cyber Defense
An open letter from cybersecurity leaders asks the U.S. government to lift export controls on Anthropic’s Fable 5 and Mythos 5, arguing that the disputed capability overlaps with normal defensive bug fixing and should be handled through transparent AI risk reviews.
JetBrains AI Plugin Malware Puts Developer API Keys at Risk
JetBrains says it removed 15 malicious Marketplace plugins that posed as AI coding tools while stealing developer API keys. Users who installed or configured the plugins should revoke affected OpenAI, DeepSeek, SiliconFlow, or other AI provider keys and check usage logs now.
NewCore’s $66M Launch Puts AI Agents Inside the Identity Stack
NewCore emerged from stealth with $66 million and an identity-security platform built for AI agents. The launch shows why enterprises need agent identities, revocation paths, and access controls before autonomous tools touch production systems.
curl’s July Security Pause Shows AI Bug Reports Have a Human Bottleneck
The curl project will pause public vulnerability reports during July 2026 after months of AI-assisted security-report pressure. The break exposes a practical risk for companies that depend on critical open source software: finding bugs is getting faster than triage, patching, and maintainer capacity.
NIST’s AI Guardrail Proof Makes Prompt Injection a Continuous Security Problem
NIST says a fixed set of AI guardrails cannot be universally robust against adaptive adversarial prompts. For teams deploying AI agents, the practical answer is continuous red-teaming, guardrail updates, access limits, and recovery planning.