Xiaoyu Li

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 across diverse watermarking methods.

The paper quantifies the cost of privacy in language identification and generation using differentially private (DP) methods, finding that the cost is surprisingly mild, particularly absent under approximate DP.

The paper proposes AgentDID, a decentralized framework using DIDs and verifiable credentials to provide trustless identity authentication and dynamic state verification for autonomous, self-managed AI agents.