Jim Miller

ironhide's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 1 month ago

Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails

Paper • 2504.11168 • Published Apr 15, 2025 • 2

Defeating Prompt Injections by Design

Paper • 2503.18813 • Published Mar 24, 2025 • 24

upvoted a collection 9 months ago

ShieldGemma

Collection

ShieldGemma is a family of models for text and image content moderation. • 4 items • Updated Jul 10, 2025 • 12