AI systems are learning to exploit loopholes in everything from software to tax law. The biggest threat may not be malicious intent, but machines doing exactly what…

October’s wave of vulnerabilities and attacks earned a stark nickname: “Black October.” But was it an unprecedented crisis—or a glimpse of what’s becoming normal? On this episode…

After a summer of sandbox escaping hacks, OpenAI said their new model was trained to be more cautious around user intent and less sensitive to “reward hacking”…

There’s a lame-duck session before Dems take over, but the leaders of the homeland security panels are already teeing up their agendas.

Former DHS CISO and acting deputy CIO Hamad Baidwan

Open-source maintainers are so overwhelmed by AI-generated security reports that some have stopped accepting them. OpenAI’s Daybreak lead says the fix is higher-quality findings and far more…

Anthropic has said out-of-control AI poses a threat to the world, but perhaps unsurprisingly suggests that profit will shape those decisions, too.

Cisco Talos' Matt Olney joins Safe Mode

One of the bill’s sponsors told CyberScoop it’s “incredibly expensive” for U.S. AI companies to stay ahead and distillation attacks incentivize stealing over innovation.

Storm-0940 used the agentic AI penetration testing framework to automate attacks and “reach more than 2,250 tenants at 2,900 sign-in attempts per minute,” Microsoft researchers said.