Defending LLMs Against Prompt Injection

UC Berkeley researchers propose StruQ and SecAlign to defend LLMs against prompt injection attacks, addressing OWASP's top threat to LLM-integrated applications.

One continuously updated timeline instead of dozens of separate articles. New developments are appended as the story evolves.

1. AnnouncementApr 11, 2025, 10:00 AM 84%

   UC Berkeley introduces StruQ and SecAlign to mitigate prompt injection attacks in LLMs

   UC Berkeley researchers propose StruQ and SecAlign to defend LLMs against prompt injection attacks, addressing OWASP's top threat to LLM-integrated applications.

   Read the full story →