LoRA-Key creates a standalone user-specific Watermark LoRA trained with a latent watermark prior and GOP, attachable via training-free superposition to protect LoRA ownership while preserving quality.
Rethinking data protection in the (generative) artificial intelligence era
6 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
6
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
RDSplat is the first 3D Gaussian Splatting watermarking method that maintains 0.701 bit accuracy against both 2D and 3D diffusion editing by embedding only in low-frequency primitives selected via FAPS.
PromptCOS is a content-only watermarking method for LLM system prompts that embeds detectable cyclic signals via auxiliary tokens while preserving fidelity and resisting removal attacks.
Coward detects backdoors in federated learning by injecting a collision-suppressed watermark on OOD data to invert the detection paradigm and limit OOD bias effects.
BiCoT embeds watermarks into the internal geometry of Chain-of-Thought reasoning traces in LLMs via private signature subspace alignment and introduces Robust Subspace Registration for black-box verification under attacks.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
LoRA-Key creates a standalone user-specific Watermark LoRA trained with a latent watermark prior and GOP, attachable via training-free superposition to protect LoRA ownership while preserving quality.
-
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
RDSplat is the first 3D Gaussian Splatting watermarking method that maintains 0.701 bit accuracy against both 2D and 3D diffusion editing by embedding only in low-frequency primitives selected via FAPS.
-
PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs
PromptCOS is a content-only watermarking method for LLM system prompts that embeds detectable cyclic signals via auxiliary tokens while preserving fidelity and resisting removal attacks.
-
Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
Coward detects backdoors in federated learning by injecting a collision-suppressed watermark on OOD data to invert the detection paradigm and limit OOD bias effects.
-
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
BiCoT embeds watermarks into the internal geometry of Chain-of-Thought reasoning traces in LLMs via private signature subspace alignment and introduces Robust Subspace Registration for black-box verification under attacks.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.