Artificial Intelligence | News, how-tos, features, reviews, and videos
AI can make SOC teams faster, but only if it fits existing workflows, connects their tools and earns analysts’ trust.
When AI agents get compromised, new research shows the model usually isn’t to blame — the code wrapped around it is. And most organizations aren’t watching it closely enough.
GPT-5.6-Cyber responded to 95% of advanced cyber requests in an OpenAI refusal-rate test and has been used to uncover previously unknown vulnerabilities in Google’s V8 engine.
IT and security leaders believe they can detect when an AI agent malfunctions or operates out of scope, but few can quickly trace and contain the cascading impact.
With the right foundation in place, the journey to a more resilient, AI-powered SOC needn’t be daunting.
Tests show the upcoming model may be able to find and exploit vulnerabilities or carry out attacks on its own, prompting stricter controls and external testing.
Researchers found that a crafted link could inject malicious instructions into Atlassian Rovo and potentially turn its broad enterprise access and autonomous agents into a data-exfiltration tool.
AI isn’t the only factor dominating the cyber market. Here’s what CISOs should know about the industry’s evolutions, as top vendors fortify platform strategies, upstarts attract VC investment, and product categories blur and emerge.
Typosquatting on popular AI services Paperclip and Browser Use, the malicious skills cracked skills.sh’s trending list, instructing agents to install a credential stealer from GitHub instead.
Frontier finds another AI model has followed OpenAI in breaking out of sandbox.
