Hacker News
- Show HN: ChatGPT Plugins are a security nightmare https://github.com/greshake/llm-security 41 comments
- Show HN: ChatGPT Plugins are a Security Nightmare https://github.com/greshake/llm-security 2 comments
- Show HN: LLMs can be susceptible to a new kind of malware https://github.com/greshake/llm-security 10 comments
Linking pages
- Edition 21: A framework to securely use LLMs in companies - Part 1: Overview of Risks https://boringappsec.substack.com/p/edition-21-a-framework-to-securely 25 comments
- Inject My PDF: Prompt Injection for your Resume https://kai-greshake.de/posts/inject-my-pdf/ 13 comments
- The Dark Side of LLMs | Medium https://medium.com/@kgreshake/the-dark-side-of-llms-we-need-to-rethink-large-language-models-now-6212aca0581a 10 comments
- GitHub - taishi-i/awesome-ChatGPT-repositories: A curated list of resources dedicated to open source GitHub repositories related to ChatGPT https://github.com/taishi-i/awesome-ChatGPT-repositories 5 comments
- The One Where Bing Becomes Chandler: A Prompt Injection Attack on Bing Chat | Vlad Iliescu https://vladiliescu.net/bing-becomes-chandler/ 1 comment
- How We Broke LLMs: Indirect Prompt Injection https://kai-greshake.de/posts/llm-malware/ 1 comment
- In Escalating Order of Stupidity https://kai-greshake.de/posts/in-escalating-order-of-stupidity/ 1 comment
- The Dark Side of LLMs | Better Programming https://betterprogramming.pub/the-dark-side-of-llms-we-need-to-rethink-large-language-models-now-6212aca0581a 0 comments
- The Dark Side of LLMs | Better Programming https://betterprogramming.pub/the-dark-side-of-llms-we-need-to-rethink-large-language-models-now-6212aca0581a?gi=a0021bd1e5d3 0 comments
Linked pages
- Prompt Injections are bad, mkay? https://greshake.github.io/ 158 comments
- GitHub - hwchase17/langchain: ⚡ Building applications with LLMs through composability ⚡ https://github.com/hwchase17/langchain 77 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
Related searches:
Search whole site: site:github.com
Search title: GitHub - greshake/llm-security: New ways of breaking app-integrated LLMs
See how to search.