LLMs are trained to block harmful responses. Old-school images can override those rules.
...moreSummary
Total Articles Found: 2
Top sources:
Top Keywords:
- LLM: 2
- AI: 1
- Biz & IT: 1
- Security: 1
- Artificial Intelligence: 1
Top Authors
- Dan Goodin: 1
- Bruce Schneier: 1
Top Articles:
- ASCII art elicits harmful responses from 5 major AI chatbots
- Data Exfiltration Using Indirect Prompt Injection
ASCII art elicits harmful responses from 5 major AI chatbots
Published: 2024-03-16 00:17:24
Popularity: 118
Author: Dan Goodin
Keywords:
Data Exfiltration Using Indirect Prompt Injection
Published: 2023-12-22 12:05:29
Popularity: 9
Author: Bruce Schneier
Keywords:
Interesting attack on a LLM: In Writer, users can enter a ChatGPT-like session to edit or create their documents. In this chat session, the LLM can retrieve information from sources on the web to assist users in creation of their documents. We show that attackers can prepare websites that, when a user adds them as a source, manipulate the LLM into sending private information to the attacker or perform other malicious activities. The data theft can include documents the user has uploaded, their chat history or potentially specific private information the chat model can convince the user to divulge at the attacker’s behest...
...more