Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails
Paper • 2504.11168 • Published • 3
Jim Miller
ironhide
AI & ML interests
Security
Recent Activity
updated a model about 1 month ago
ironhide/shieldgemma-awq-2b liked a model about 1 month ago
ironhide/shieldgemma-awq-2b published a model about 1 month ago
ironhide/shieldgemma-awq-2bOrganizations
None yet
upvoted 2
papers 2 months ago