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.
Apple Removed Apps Infested With Screen Reading Malware
Kaspersky reported the discovery of “SparkCat” malware in some iOS apps. Apple subsequently removed 11 infested apps from the App Store and found another 89
