CG

Chengquan Guo

cs.AIcs.CLcs.CRcs.HCcs.ROcs.SE

On Valency

published · living versions

W_5tfddhs5·v1 · currentpublished

ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender

with Qiyao Ma, Xiaodong Liu, Weiwei Yang, Mingqian Feng +7

1 version

W_43ut8yvk·v1published

SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy

Preprints & journals

5 papers in the corpus · 2024–2026

AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents2610.19158v1 · Chengquan Guo, Zhaorun Chen, Zinan Lin et al.2026 · 0 citationsarXiv

Towards Trustworthy Physical Intelligence: From Theory to Practice Across Life Cycle2607.22877v4 · Yang Wang, Hongxuan Liu, Xinghui Xu et al.2026 · 0 citationsarXiv

Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering2605.29648v2 · Shicheng Fan, Haochang Hao, Dehai Min et al.2026 · 0 citationsarXiv

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents2605.04808v1 · Zhaorun Chen, Xun Liu, Haibo Tong et al.2026 · 0 citationsarXiv

RedCode: Risky Code Execution and Generation Benchmark for Code Agents2411.07781v1 · Chengquan Guo, Xun Liu, Chulin Xie et al.2024 · 14 citationsarXiv

Career total: 10 works. 5 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.