BRIGHTMIND AI
Simple AI, tools, research, and future-skills updates

ChatGPT Memory Flaw: How Hackers Could Exploit AI to Steal Your Data

Recently, security researcher Johann Rehberger uncovered a vulnerability in ChatGPT’s memory feature, which allowed attackers to store false information and harmful instructions in a user’s long-term memory settings. Despite this discovery, OpenAI initially dismissed it as a safety issue rather than a security threat.

Refusing to back down, Rehberger demonstrated how this vulnerability could be exploited by creating a proof-of-concept (PoC) that extracted all user input continuously. This caught OpenAI’s attention, prompting them to release a partial fix earlier this month.

The Vulnerability Exploited Memory Features

The flaw involved ChatGPT’s long-term memory feature, introduced in February and expanded in September. This feature allows ChatGPT to remember details like a user’s preferences and past conversations, making future interactions smoother. However, Rehberger found that attackers could abuse this feature through indirect prompt injection—a technique that makes the AI follow instructions from untrusted sources such as emails or blog posts.

Using this method, Rehberger demonstrated how he could manipulate ChatGPT into permanently storing false information. For instance, he made the AI believe a user was 102 years old, lived in a fictional world, and believed Earth was flat. These fabricated details then influenced all future conversations.

The attack didn’t stop there. Rehberger also showed how malicious files hosted on platforms like Google Drive or Bing could be used to plant these false memories, making the flaw a real threat.

OpenAI’s Response and Ongoing Risks

Rehberger reported the issue to OpenAI in May, but the company initially closed the case. A month later, after submitting a more detailed report and PoC, OpenAI engineers took action. His PoC revealed that by tricking ChatGPT into viewing a malicious web link, all user interactions could be copied to a server controlled by the attacker. This was especially concerning because the data exfiltration persisted across multiple sessions.

While OpenAI has fixed part of the problem by preventing memory abuse for data exfiltration, Rehberger noted that prompt injections can still be used to plant long-term false information.

Staying Safe

To avoid these types of attacks, users should be cautious when new memories are added during sessions and regularly review stored memories for anything unusual. OpenAI offers tools for managing and reviewing these memories, but the issue of prompt injections still lingers.

Stay informed on security updates and other tech insights at brightmindai.com!

Read about: Is your Job safe from AI

Can AI generate better ideas than HUMAN?

I can’t focus on my studies-mobile scrolling-lazy and unmotivated

Can AI Help Fix Political Divides? Insights from Duke Professor Christopher Bail

Scientists solved the mystery of how the great pyramids of Egypt were constructed

Newsfeed
Latest Technology & Education News

More for you

No Results Found

The page you requested could not be found. Try refining your search, or use the navigation above to locate the post.

Person typing on a MacBook, illustrating Gemini computer use automating Mac tasks

What Is Gemini Computer Use on Mac? Google’s New AI Agent Explained

Google just gave the Gemini app for Mac a new computer use ability that clicks, types, and fills forms for you. Here’s what it actually does and how to try it.

Abstract blue light representing the new Claude Fable 5.2 AI model update

What Is Claude Fable 5.2? Anthropic’s Most Powerful AI Model Just Got an Upgrade

Anthropic’s Claude Fable 5.2 and Claude Mythos 5.2 are here. We break down what changed, who gets access to Mythos, and what it actually means for everyday Claude users.

Student studying with a laptop in a library, using Gemini Notebook study tools

Gemini Notebook’s New Study Tools: Voice Chat, Quizzes, and a Free Year of Google AI Pro

Gemini Notebook, formerly NotebookLM, just added voice chat, new quiz formats, and video overviews, plus a free year of Google AI Pro for college students who redeem it by December 31, 2026.

0 Comments

Submit a Comment

Your email address will not be published. Required fields are marked *

Verified by MonsterInsights