Threat actors tailor prompt-injection tricks—not for humans, but AI
Phishers want to overwhelm AI-based systems with lots of boring text.
Phishers want to overwhelm AI-based systems with lots of boring text.
One security pro provides a red-flag list for HR.
“Functionally, what [LLMs] change about security dynamics is the velocity of exploit development and the cost of the discovery of vulnerabilities,” Expel Director of Threat Operations James Shank says.
Microsoft says the campaign leveraged “polished, enterprise-style HTML templates” and other elements to appear more convincing.
AI might get too good for the normal checks within the next two years, experts say.
A lot depends on IT pros’ diligence when it comes to setting up AI agents.
“Attackers gain disproportionate benefit, and current patch cycles, response processes, and risk metrics were not built for this environment,” the CSA memo noted.
From cybersecurity and big data to cloud computing, IT Brew covers the latest trends shaping business tech in our 4x weekly newsletter, virtual events with industry experts, and digital guides.
By subscribing, you accept our Terms & Privacy Policy.