Author

Zhengyue Zhao

h-index 3 View on Semantic Scholar

We have 3 of 6 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Safety Mid-Training: Internalizing LLM Safety as a Foundational Capability

Safety alignment for large language models (LLMs) is primarily performed during post-training, while recent work has also begun incorporating safety data into pre-training. Yet safety can degrade when later training no longer includes safety data, and gains in safety often come at the cost of general capability. This t...

Zheng-Yue Zhao, Li-Wei Jiang, Ye-Jin Choi et al. · 0 citations

Preprint Aug 2026

Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services

It is proved that the achievable security and utility tradeoff depends entirely on how benign requests for the same capabilities are grouped, and that the achievable security and utility tradeoff depends entirely on how persistent, recognizable groups permit a useful defense.

Bowen Sun, Zhengyue Zhao, Xiaogeng Liu et al. · 1 citation

Preprint Aug 2026

KeyPooling: Measuring Where LLM API Relay Paths Collapse Prompt Cache Isolation

KeyPooling is presented, a measurement method that traces customer identity through cache lookup and write, verifies runtime transformations, and tests one predicted identity component at a time, and derives a defense contract.

Bowen Sun, Yixi Cai, Xiaogeng Liu et al. · 0 citations