Linking pages
- AI Malware: A Silent and Looming Threat in A New Era of Cybersecurity Risks https://www.maginative.com/article/ai-malware-a-silent-and-looming-threat-in-a-new-era-of-cybersecurity-risks 1 comment
- In Escalating Order of Stupidity https://kai-greshake.de/posts/in-escalating-order-of-stupidity/ 1 comment
- Invisible Indirect Injection: A Puzzle for ChatGPT https://kai-greshake.de/posts/puzzle-22745/ 0 comments
Linked pages
- Introducing Microsoft 365 Copilot – your copilot for work - The Official Microsoft Blog https://blogs.microsoft.com/blog/2023/03/16/introducing-microsoft-365-copilot-your-copilot-for-work/ 399 comments
- Prompt Injections are bad, mkay? https://greshake.github.io/ 158 comments
- The Dual LLM pattern for building AI assistants that can resist prompt injection https://simonwillison.net/2023/Apr/25/dual-llm-pattern/ 116 comments
- openai-python/chatml.md at main · openai/openai-python · GitHub https://github.com/openai/openai-python/blob/main/chatml.md 78 comments
- GitHub - greshake/llm-security: New ways of breaking app-integrated LLMs https://github.com/greshake/llm-security 53 comments
- Announcing new generative AI experiences in Google Workspace | Google Workspace Blog https://workspace.google.com/blog/product-announcements/generative-ai 34 comments
- Ihr täglicher KI-Begleiter | Microsoft Bing https://www.bing.com/new 27 comments
- [2302.12173] Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection https://arxiv.org/abs/2302.12173 26 comments
- Three ways AI chatbots are a security disaster | MIT Technology Review https://www.technologyreview.com/2023/04/03/1070893/three-ways-ai-chatbots-are-a-security-disaster/ 22 comments
- Hackers Can Turn Bing's AI Chatbot Into a Convincing Scammer, Researchers Say https://www.vice.com/en/article/7kxzzz/hackers-bing-ai-scammer 8 comments
- The Hacking of ChatGPT Is Just Getting Started | WIRED https://www.wired.com/story/chatgpt-jailbreak-generative-ai-hacking/ 3 comments
Related searches:
Search whole site: site:kai-greshake.de
Search title: How We Broke LLMs: Indirect Prompt Injection
See how to search.