I tested my prompts for vulnerability to messages like “IGNORE ALL PREVIOUS INSTRUCTIONS” and often such messages worked. I would like to study methods of protection against such attacks. There are several articles on the web about this, but I would like to know what works best specifically for Gemini. Thank you in advance.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Testing Approach Inquiry for Google AI Studio Prompts | 2 | 193 | May 20, 2024 | |
| Virtual Voice Assistant | 0 | 61 | December 20, 2024 | |
| Enhancing Conversation Continuity in Future Gemini APIs | 0 | 99 | November 16, 2024 | |
| How can i turn off safty for my Gemini Api | 2 | 260 | August 22, 2024 | |
| I’m trying to understand how | 0 | 37 | September 27, 2024 |