Welcome to our

Cyber Security News Aggregator

.

Cyber Tzar

provide a

cyber security risk management

platform; including automated penetration tests and risk assesments culminating in a "cyber risk score" out of 1,000, just like a credit score.

Hacking ChatGPT by Planting False Memories into Its Data

published on 2024-10-01 11:07:34 UTC by Bruce Schneier
Content:

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.

Article: Hacking ChatGPT by Planting False Memories into Its Data - published 3 days ago.

https://www.schneier.com/blog/archives/2024/10/hacking-chatgpt-by-planting-false-memories-into-its-data.html   
Published: 2024 10 01 11:07:34
Received: 2024 10 01 11:20:54
Feed: Schneier on Security
Source: Schneier on Security
Category: Cyber Security
Topic: Cyber Security
Views: 0

Custom HTML Block

Click to Open Code Editor