Cybersecurity researchers managed to bypass security precautions on ChatGPT, a chatbot by OpenAI, and used it to write malware capable of accessing Google Chrome’s password manager. By engaging the chatbot in a role-playing scenario, the researchers were able to convince it to script such malicious code. OpenAI said the behavior was consistent with the model, as its output depends on user prompts.
Wipers from Russia’s most cut-throat hackers rain destruction on Ukraine
One of the world’s most ruthless and advanced hacking groups, the Russian state-controlled Sandworm, launched a series of destructive cyberattacks in the country’s ongoing war
