RAPID: A Real-Time Defense Against Unauthorized Model Distillation for Text-to-Image Services
cs.CR
Submitted: 2026-09-14
Updated: 2026-09-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- HMARK: Radioactive Multi-Bit Semantic-Latent Watermarking for Diffusion Models
- Auto-Encoding Variational Bayes
- Denoising Diffusion Implicit Models
- Distilling the Knowledge in a Neural Network
- Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
- Explaining and Harnessing Adversarial Examples
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
- LoRA: Low-Rank Adaptation of Large Language Models
- Countering Adversarial Images using Input Transformations
- Mitigating Adversarial Effects Through Randomization
- Data Poisoning Won't Save You From Facial Recognition
- Unlearnable Examples: Making Personal Data Unexploitable
- Delving into Transferable Adversarial Examples and Black-box Attacks
- On Improving Adversarial Transferability of Vision Transformers
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs