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…

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…

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…

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…

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…

The paper proposes a Jacobian-guided anisotropic noise reshaping technique to selectively attenuate noise in task-relevant subspaces, significantly enhancing data utility while maintaining Local Diffe…

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.

The paper introduces the linear canonical Riesz potential (LCRP) and analyzes its convergence properties, leveraging these findings to propose a novel, secure, and efficient asymmetric cascaded LCRP m…

The paper argues that watermarking must be viewed as a monitoring primitive, introducing an observer-based threat model that shows even zero-bit watermarking can enable entity-level attribution throug…

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…

The paper proposes a multi-ciphertext privacy-preserving framework to efficiently compute high-resolution image gradients using Fully Homomorphic Encryption (FHE) by dividing the large image into smal…

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

This paper compares modern and classic post-hoc watermarking methods, concluding that classic techniques offer superior security and robustness in realistic scenarios compared to modern neural network…

ArmSSL is a novel watermarking framework that provides robust, black-box ownership verification for self-supervised learning encoders while maintaining high utility and resisting adversarial attacks.

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 introduces S2MDF, a plug-and-play module that enforces a hard constraint to eliminate interpenetrations in multi-object Signed Distance Field (SDF) representations, significantly improving p…

The paper enhances the security of the PolyProtect biometric template protection method by proposing a key selection algorithm that significantly increases the difficulty of inverting protected face t…

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…

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…