In a fresh development, openAI has launched a fresh security capability in ChatGPT called Lockdown Mode, designed to provide additional protection against so-called “prompt injection attacks.”.
The report highlights that a prompt injection attack is when someone crafts a deceptive prompt in an attempt to trick the LLM into following malicious instructions and/or revealing sensitive information.
The report highlights that prompt injection attacks have been used to do all sorts of things, like hijacking Perplexity’s AI browser, controlling smart home devices via Google Gemini, and stealing personal information via compressed images and Google Calendar. These deceptive prompts are often hidden within web pages and other data sources, which are easily missed by humans but still read and processed by LLMs.
The report highlights that first unveiled back in February, Lockdown Mode will now restrict and/or disable several ChatGPT functions when enabled, including live web browsing (in favor of cached content), the retrieval and display of web-based images, Deep Research, and Agent Mode.
According to the latest update, openAI emphasizes that this capability can’t completely eliminate the risk of prompt injection attacks, as malicious instructions could always be present in uploaded files or cached content.
As part of the ongoing story, if you aren’t seeing Lockdown Mode in your settings, it may not have rolled out to you yet and you’ll have to wait a bit longer for it. As of this writing, Lockdown Mode is rolling out to all ChatGPT account types, including Free, Go, Plus, and Pro plans.
As part of the ongoing story, this article originally appeared on our sister publication PC för Alla and was translated and localized from Swedish.
In a fresh development, he is passionate about technology and is on the ball with the most recent product drops and the hottest talking points in the consumer tech industry. Viktor writes news and reports for our sister sites, M3 and PC för Alla.