A security researcher discovered a way to exploit ChatGPT's memory feature to steal user data. However, the exploit requires users to click on a malicious link and only works with the macOS version of ChatGPT. OpenAI has already fixed the vulnerability.
As a longtime ChatGPT user, I want AI chatbots to be very secure and private. That is, I want the contents of my chats to be protected from would-be attackers and from OpenAI itself. OpenAI can of course use chats to train future models if you allow it, but I don't. While I have to trust that OpenAI handles the security and privacy aspects of the ChatGPT experience, I also know that other ChatGPT enthusiasts will test everything that's possible with the chatbot.
Assuming you click on the malicious link and you have the Mac app, you can instruct ChatGPT to explain what it is about, as you'll see in the proof-of-concept video at the end of this post. ChatGPT will most likely fail to identify that it's now spying on your chats for a third party. Here's the final twist: You still control the memory. OpenAI introduced the ChatGPT memory feature earlier this year to improve your conversations with ChatGPT.
Chatgpt Security Privacy Exploit Openai
Malaysia Latest News, Malaysia Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
OpenAI unveils new ChatGPT models designed to tackle complex problemsTsveta, a passionate technology enthusiast and accomplished playwright, combines her love for mobile technologies and writing to explore and reveal the transformative power of tech.
Read more »
OpenAI's New ChatGPT o1: The Reasoning Powerhouse That Thrives on ClarityOpenAI's latest ChatGPT model, ChatGPT o1, is a game-changer for businesses and individuals alike. This new version prioritizes clarity and conciseness, understanding your requests even without lengthy explanations. It excels at grasping context, reading between the lines, and offering considered responses thanks to its internal reasoning process.
Read more »
OpenAI Says It's Fixed Issue Where ChatGPT Appeared to Be Messaging Users UnpromptedScience and Technology News and Videos
Read more »
ChatGPT Appears To Message Users Unprompted, OpenAI InvestigatingOpenAI is investigating an incident where ChatGPT appeared to message users without being prompted. The chatbot reportedly asked a user 'How was your first week at high school?' The company claims the error occurred due to a previous message not being delivered correctly.
Read more »
OpenAI is testing 8 new voices for ChatGPT that could launch soonThrough reverse engineering, ChatGPT users have uncovered 8 new voices for OpenAI's chatbot that have yet to be announced.
Read more »
Rumors about OpenAI 'Strawberry' model indicate a more 'thoughtful' generative AI to come to ChatGPTIzzy, a tech enthusiast and a key part of the PhoneArena team, specializes in delivering the latest mobile tech news and finding the best tech deals. Her interests extend to cybersecurity, phone design innovations, and camera capabilities.
Read more »