Lessons from Defending Gemini Against Indirect Prompt Injections Paper • 2505.14534 • Published May 20, 2025 • 8
Humans expect rationality and cooperation from LLM opponents in strategic games Paper • 2505.11011 • Published May 16, 2025 • 5
Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography Paper • 2501.08970 • Published Jan 15, 2025 • 6
Operationalizing Contextual Integrity in Privacy-Conscious Assistants Paper • 2408.02373 • Published Aug 5, 2024 • 5
