Subject
2 entries
LLM Security
Bookmarks
Resilient Cyber's Collection of AI Security Resources
Resilient Cyber's curated collection of AI security resources: interviews, publications, and frameworks covering LLM threat models, red teaming, and AI-specific attack surfaces. A useful aggregation point for the AI security practitioner landscape.
Data Exfiltration from Writer.com via Indirect Prompt Injection
PromptArmor and Kai Greshake demonstrate data exfiltration from Writer.com via indirect prompt injection — where malicious content in a document the AI assistant processes causes it to leak user data. A concrete case study of the class of attack affecting all document-processing LLM applications.