An engineer from CyberArk has challenged the safety protections of OpenAI’s latest o3-mini model just days after its launch. He was able to get the model to teach him how to write an exploit for a Windows security process, which was achieved by posing as an student requesting educational information. Although the model features a new security feature called “deliberative alignment”, it still proved to be susceptible to certain manipulations.
Infostealers Aimed At MacOS Surges
MacOS-targeted information-stealing malware spiked by 101% in the latter half of 2024, making up most of macOS’s malware that year. Despite their limited capacity, these
