Zhiyi Tian
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2ML×1
Frequent co-authors
Research Timeline
2026
Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling
The paper proposes Ellipsoid Control, a white-list defense mechanism that uses benign data geometry to constrain model updates, thereby enhancing jailbreak safety while preserving the utility of harmless inputs.
Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
The paper proposes an unsupervised bi-level adversarial training framework to enhance LLM safety steering, achieving strong zero-shot defense against unseen and evolving jailbreak prompts.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 23, 2026
Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling
Luoyu Chen, Weiqi Wang, Zhiyi Tian, Feng Wu +2 more
The paper proposes Ellipsoid Control, a white-list defense mechanism that uses benign data geometry to constrain model updates, thereby enhancing jailbreak safety while preserving the utility of harml…
View →
cs.CRcs.LGRecentMay 23, 2026