The paper demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output fro…

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

This paper proposes a neural audio watermarking method that embeds a message into the continuous latent representation of a codec-like speech autoencoder for improved codec robustness.

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.

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

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…

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…

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 a theoretically grounded evaluation framework for watermarking generative models, proposing a novel method (SSB) that allows for systematic design across all security-robustness-f…

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…

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 introduces SHIFT, a training-free attack that exploits the vulnerability of diffusion-based watermarking by stochastically deflecting the generative trajectory, achieving high removal rates…

This paper introduces SSTMark, a training-free speech watermarking framework that encodes watermark information into the semantic content of generated speech.

This paper proposes using a Diffusion Transformer as a frozen reconstruction probe for audio deepfake detectors, achieving state-of-the-art performance on ASVspoof 5 Eval and ITW Full.

This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…

The paper proposes Asymmetric Phase Coding (APC), a training-free cryptographic audio watermarking scheme that achieves high extraction rates (97.5%-98.3%) across various real-world and adversarial at…