Get started
Author

Shuchao Pang

Observed name: Pang, Shuchao
OpenAlex ID: A5130625566
Reconstruction of Differentially Private Text Sanitization via Large Language Models
2025 · Shuchao Pang, Zhigang Lu, et al. · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · 16
PDF
DREAM: Dynamic Red-teaming across Environments for AI Models
2025 · Lu, Liming, Gu, Xiang, et al. · arXiv (Cornell University) · 4
PDF
If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
2026 · Chang, Jiamin, Xue, Minhui, et al. · arXiv (Cornell University) · 3
PDF
AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
2026 · Luo, Yutao, Zhu, Haotian, et al. · arXiv (Cornell University) · 3
PDF
FirmPilot: Evidence-Driven Validation of Vulnerability Reports in Linux-Based IoT Firmware
2026 · Peng, Xuekang, Li, Haipeng, et al. · Zenodo (CERN European Organization for Nuclear Research)
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
2026 · Lian, Yuefang, Guo, Longkun, et al. · arXiv (Cornell University)
PDF
AI Alignment through a Game-theoretic Lens: A Survey
2026 · Yanan Cai, Zhongrui Zhao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
CLEAR: A Clean-Label Backdoor Attack via Representation-Guided Trigger Embedding
2025 · Zhan Wu, Haipeng Li, et al. · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics
Works count: 8
Citation count: 26
H-index: 3
I10-index: 1
Year
Topic
Type