Jian Zhang

This paper develops improved Gaussian mechanisms for Rényi Pufferfish Privacy (RPP) by incorporating Gaussian and Gaussian-mixture priors, significantly reducing the required noise and improving the privacy-utility trade-off.

This paper introduces an active traffic analysis method (NATA) and a deep learning framework (BM-Net) to demonstrate that bandwidth perturbations can be used by an adversary to correlate and de-anonymize Tor traffic flows.

The paper introduces the $\alpha$-Wasserstein mechanism to achieve Rényi Pufferfish Privacy using Laplace and Gaussian noise, demonstrating that it generalizes existing privacy frameworks and reduces noise power.

The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits this region.

The paper introduces PRISM, a novel representation learning framework that learns isometric embeddings by explicitly modeling the intrinsic geodesic metric of 3D surfaces, achieving superior performance on various geometric tasks.

OctoT2I introduces a self-evolving, agentic routing framework that efficiently selects and combines multiple Text-to-Image models, achieving high performance while significantly boosting inference speed and energy efficiency.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.