Get started
Author

Siyuan Liang

Observed name: Liang, Siyuan
ORCID: 0000-0002-6154-0233
Observed ORCID: 0000-0002-6154-0233
OpenAlex ID: A5126716016
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
2026 · Siyuan Liang, Jiayang Liu, et al. · International Journal of Computer Vision · 2
PDF
TrojanWorld: Backdooring World-Model Agents via Imagination Steering
2026 · Huang, Wenkai, Liang, Siyuan, et al. · arXiv (Cornell University)
PDF
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents
2026 · Wang, Jiancheng, Zhu, Mingli, et al. · arXiv (Cornell University)
PDF
SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense
2026 · Liang, Siyuan, Qiu, Yupeng, et al. · arXiv (Cornell University)
PDF
Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
2026 · Li, Xuebin, Zhao, Hanqing, et al. · arXiv (Cornell University)
PDF
SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks
2026 · Li, Siyuan, Wulianghai, Aodu, et al. · arXiv (Cornell University)
PDF
Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
2026 · Qi, Leyi, Li, Yiming, et al. · arXiv (Cornell University)
PDF
WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents
2026 · Guo, Zhixiang, Liang, Siyuan, et al. · arXiv (Cornell University)
PDF
When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models
2026 · Guo, Zhixiang, Liang, Siyuan, et al. · arXiv (Cornell University)
PDF
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
2026 · Association for Artificial Intelligence 2026, Liang, Siyuan, et al. · Underline Science Inc.
Works count: 11
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type