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.
Chinese Hackers Target European Diplomats with Malware
MirrorFace, a threat actor tied to Chinese cyberespionage, has expanded its activity outside East Asia, targeting a European organization with updated hacking tools. Researchers from
