activity
20242026
collaborators

11 papers

cs.CR2026

PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking

Haiyu Deng, Yanna Jiang, Guangsheng Yu +5

Our evaluation shows that PoLO achieves \textbf{99\%} watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just…

cs.CR2026

Clawed and Dangerous: Can We Trust Open Agentic Systems?

Shiping Chen, Qin Wang, Guangsheng Yu +2

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and e…

cs.CR2026

PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents

Guangsheng Yu, Qin Wang, Rui Lang +2

Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordinating tools and guiding execution over local environments. In many deployment…

cs.CE2026

In the Margins: An Empirical Study of Ethereum Inscriptions

Xihan Xiong, Minfeng Qi, Shiping Chen +3

Ethereum Inscriptions (Ethscriptions) repurpose Ethereum calldata into a persistent inscription channel by embedding \texttt{data:}~URI payloads. These transactions typically targe…

cs.CR2026

Why Neural Structural Obfuscation Can't Kill White-Box Watermarks for Good!

Yanna Jiang, Guangsheng Yu, Qingyuan Yu +2

Neural Structural Obfuscation (NSO) (USENIX Security'23) is a family of ``zero cost'' structure-editing transforms (\texttt{nso\_zero}, \texttt{nso\_clique}, \texttt{nso\_split}) t…

cs.CR2026

Client-Cooperative Split Learning

Haiyu Deng, Yanna Jiang, Guangsheng Yu +5

Model training is increasingly offered as a service for resource-constrained data owners to build customized models. Split Learning (SL) enables such services by offloading trainin…