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 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.

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…

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…

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 AnaFP, a theoretically guided analytical fingerprinting scheme that determines the optimal distance of a model's fingerprint from the decision boundary to ensure both robustness and…

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…

DeepSignature proposes a novel, cryptographically verifiable watermarking system that uses deep neural networks to embed digital signatures into images, enabling robust source attribution and near 100…

The paper proposes W-IR, a novel watermarking framework that simultaneously achieves high certified robustness against adversarial attacks and effectively mitigates identity leakage in watermarked ima…

The paper proposes a simple, generic attack strategy—re-watermarking—that reliably suppresses existing watermarks, demonstrating that watermarks can be used to attack other watermarks.

MATRIX is a novel, robust code watermarking framework that encodes watermarks using constrained parity-check matrix equations, achieving high detection accuracy and improved robustness for code proven…

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…

Rel-Zero proposes a novel zero-watermarking technique that embeds invisible watermarks by exploiting the invariance of relational distances between image patches during AI editing, achieving superior…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

The paper proposes GeoMark, a geometry-aware localized watermarking framework that robustly protects Embedding-as-a-Service (EaaS) against model stealing and copyright infringement while preserving ut…

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 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 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…