AI Unlocked Decoding Prompt Injection Interactive Challenge
• AI Unlocked challenge focuses on detecting and mitigating prompt injection attacks. • Participants learn to craft prompts that resist malicious manipulation by LLMs. • Interactiv
Promptinjection
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
• LLMs power new apps but prompt injection is top OWASP threat. • Attack injects malicious instructions into untrusted data, overriding trusted prompts. • Real-world examples: Yelp