End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery
Normal Alignment: Improved Cryptanalytic Sign Recovery on Hard-Label Networks
RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services
1
Shuffling is Not Enough: Breaking Permutation-Based Model Confidentiality in Hybrid FHE Inference
1
US Government Accuses Chinese AI Firms of Distilling Frontier Models
in the wild1
US Agencies Warn Chinese AI Firms Are Extracting Advanced AI Models
in the wild 5 min1
Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection
CISA Warns Chinese AI Firms Extract Billions of Tokens From Claude, GPT, Gemini and Grok
in the wild 4 min