The paper proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting i…

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…

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…

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.

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

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 introduces RLSpoofer, a lightweight, black-box reinforcement learning attack that demonstrates the fragile resilience of current LLM watermarking schemes by achieving a high spoofing success…

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…

VOW introduces a novel, privacy-preserving, and cryptographically verifiable protocol for detecting watermarks in LLM-generated text, overcoming the limitations of centralized and non-verifiable exist…

The paper introduces BREW, a novel framework that significantly improves the reliability of multi-bit text watermarking for LLMs by replacing flawed decoding-centric methods with a designated two-stag…

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…

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying PRNG, thereby amplifying the watermark without altering the…

This paper introduces 'implicit identity' as a unifying framework to survey and categorize LLM fingerprinting and watermarking techniques for verifying ownership and provenance across datasets, models…

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.

SWAN introduces a novel, training-free framework that embeds watermarks directly into the semantic structure of a sentence using Abstract Meaning Representation (AMR), achieving superior robustness ag…

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

The paper demonstrates a class of steganographic exfiltration attacks against vector databases by hiding data within embeddings, and proposes VectorPin, a cryptographic provenance protocol to detect s…

Dual-Guard introduces a dual-channel latent watermarking framework that simultaneously embeds global provenance and localized content anchors into diffusion images, achieving robust detection against…

TimeMark proposes a trustworthy time watermarking framework that uses cryptographic techniques and error-correcting codes to achieve 100% accurate recovery of the generation time from AIGC, resisting…

The paper proposes a novel binomial multibit LLM watermarking scheme that encodes every bit of a payload at every token position, achieving superior message accuracy and robustness compared to existin…