The paper proposes Functional Subspace Watermarking (FSW), a robust method that embeds ownership signals into a stable, low-dimensional functional subspace of LLMs, significantly improving detection a…

PASA introduces a robust, semantic-level watermarking technique that embeds and detects watermarks in the latent embedding space, successfully resisting semantic-invariant attacks like paraphrasing.

This paper analyzes existing watermarking schemes for autoregressive image generators and demonstrates that they are vulnerable to various removal and forgery attacks, suggesting they are unreliable f…

XMark introduces a novel multi-bit watermarking technique that reliably embeds binary messages into LLM-generated text while maintaining high text quality and robust performance even with limited toke…

The paper demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

The paper introduces LUNA, a linguistically adaptive watermarking technique that achieves high detection accuracy across diverse languages while maintaining minimal text distortion, outperforming exis…

The paper proposes SSG, a novel logit-balanced vocabulary partitioning method, to enhance the watermark strength and detectability of LLM-generated content, especially in low-entropy domains like code…

The paper introduces 'infilling extraction' to accurately model training data memorization in Diffusion Language Models (DLMs), finding that bidirectional masking significantly increases the extractab…

VertMark introduces a novel, unified, and training-free framework to embed robust watermarks into vertical domain pre-trained language models (VPLMs) for copyright protection across multiple specializ…

The paper proposes Cert-LAS, a novel certified method for verifying model ownership in text-to-image diffusion models, which is robust against malicious signal removal attacks.

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright prot…

The paper proposes Adaptive Stealing (AS), a novel and more robust watermark stealing algorithm that dynamically selects optimal attack perspectives to significantly increase the efficiency of comprom…

The paper analyzes the robustness of current LLM watermarking schemes against various text modifications, concluding that watermarks can be removed with reasonable effort.

TextSeal is a novel, non-overhead, and robust watermark for LLMs that enables accurate provenance tracking and detection of unauthorized use even after model distillation.

Gaussian Shannon proposes a novel watermarking framework that treats diffusion generation as a noisy communication channel, enabling both robust tracing and exact bit-level recovery of embedded waterm…

This paper develops provably undetectable and robust watermarking schemes for LLM outputs even when the per-token entropy is only constant, removing previous dependencies on high entropy rates or larg…

The paper proposes a novel proof-of-authorship framework for AI-generated content by cryptographically binding the random seed used in latent diffusion model generation to the author's identity, offer…

The paper introduces SHADOWMASK, the first systematic backdoor attack targeting Masked Diffusion Language Models (MDLMs), demonstrating near-100% attack success while preserving clean model utility.

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying Pseudo-Random Number Generator (PRNG) without altering the g…