Prompt injection attacks pose a serious threat to anyone who uses AI tools, but especially to professionals who rely on them at work. By exploiting a vulnerability that affects most AIs, a hacker can insert malicious code into a text prompt, which may then alter the results or even steal confidential data. Also: 5 custom ChatGPT instructions I use to get better AI results - faster Now, OpenAI has introduced a feature called Lockdown Mode to better thwart these types of attacks.
A little known security feature on iPhones is in the spotlight after it stymied efforts by U.S. federal authorities to search devices seized from a reporter.Apple's Lockdown Mode recently prevented FBI agents from getting into Washington Post reporter Hannah Natanson's iPhone.Agents seized the phone, as well as two MacBooks and other electronic devices, when they searched Natanson's home last month as part of an investigation into a Pentagon contractor accused of illegally handling classified information.