Hacking ChatGPT by Planting False Memories into Its Data

This vulnerability hacks a feature that allows ChatGPT to have long-term memory, where it uses information from past conversations to inform future conversations with that same user. A researcher found that he could use that feature to plant “false memories” into that context window that could subvert the model.

A month later, the researcher submitted a new disclosure statement. This time, he included a PoC that caused the ChatGPT app for macOS to send a verbatim copy of all user input and ChatGPT output to a server of his choice. All a target needed to do was instruct the LLM to view a web link that hosted a malicious image. From then on, all input and output to and from ChatGPT was sent to the attacker’s website.

Tags: , ,

Posted on October 1, 2024 at 7:07 AM • 0 Comments

<

p id=”powered”>Sidebar photo of Bruce Schneier by Joe MacInnis.

Discover more from Cyber Elias Academy

Subscribe to get the latest posts sent to your email.

Leave a Reply

Explore More

Security leaders discuss the U.S. Treasury’s concerns regarding AI

The U.S. Department of the Treasury released a report stating that artificial intelligence (AI) is contributing to an increase in financial fraud. The agency states that AI has allowed for

Read More

Volcano Demon Ransomware Group Rings Its Victims To Extort Money

What’s happening? Security researchers have warned that a new ransomware group has taken an unusual twist on the traditional method of extorting money from its corporate victims. So what’s different

Read More

RaaS Group Targets Corporate Networks with SharpRhino RAT

The Hunters International ransomware gang targets IT professionals with SharpRhino remote access trojan (RAT). The malware spoofs the installer of Angry IP Scanner, an ethical hacking tool. Hunters International is

Read More