Our latest report reveals how AI is reshaping our relationships, blurring what feels authentic, and creating new ways for intimacy to be exploited.
Interesting research: “ AI Models Can Provably Hide Arbitrary Capabilities ” Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks…
ISC2 is seeking 3000 volunteers to enrol to a pilot exam phase for its upcoming AI security certification
Before you turn yourself into a zombie, check who’s getting your photos. Some Halloween AI sites offer little information about who's behind them.
Imagine buying a brand new hardware wallet for your cryptocurrency with the shrink-wrap still on... what could possibly be hiding inside? We break out a Geiger counter and a cat to find out. Meanwhile, malicious ads are targeting journalists with zero-click attacks. Plus, Origin’s Spencer Thompson reveals what AI agents are really getting up to on your employees’ laptops when nobody’s looking.…
As AI lets anyone build software, here’s how to vet that shiny new app before it exposes your data
As AI opens new paths to company data while making familiar attacks faster and cheaper, SMBs need protection designed around the time and expertise available to operate it
As AI adoption expands the attack surface and adds to the security workload, businesses need automation backed by experts
Don’t panic if you spot an illegally created image or video of you online – there are ways to request its removal