Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zijian Zhang

Zijian Zhang

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×3ML×1NLP×1

Frequent co-authors

Zhen Li2×
Liehuang Zhu2×
Ni Ding2×
Wenjin Yang2×
Rizhen Hu1×
Athanasios Glentis1×

Research Timeline

2026
Rényi Pufferfish Privacy with Gaussian-based Priors: From Single Gaussian to Mixture Model

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.

ActiveFlowMark: Assessing Tor Anonymity under Active Bandwidth Watermarking

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.

$α$-Wasserstein Mechanism for Rényi Pufferfish Privacy

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.

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

This paper studies the distribution of reinforcement learning (RL) adaptation across transformer layers in large language models and finds that training a single layer can recover most of the gains obtained during full RL training.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.CLEmpiricalRecentJul 1, 2026

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li +3 more

This paper studies the distribution of reinforcement learning (RL) adaptation across transformer layers in large language models and finds that training a single layer can recover most of the gains ob…

View →
cs.CRRecentMay 7, 2026

ActiveFlowMark: Assessing Tor Anonymity under Active Bandwidth Watermarking

Zilve Fan, Zijian Zhang, Yangnan Guo, Jiaqi Gao +4 more

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-anonym…

View →
cs.CRRecentMay 7, 2026

$α$-Wasserstein Mechanism for Rényi Pufferfish Privacy

Ni Ding, Wenjin Yang, Zijian Zhang

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…

View →
cs.CRRecentApr 26, 2026

Rényi Pufferfish Privacy with Gaussian-based Priors: From Single Gaussian to Mixture Model

Wenjin Yang, Ni Ding, Zijian Zhang, Zhen Li +4 more

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 p…

View →