Get started
Author

Tianhang Zheng

Observed name: Zheng, Tianhang
OpenAlex ID: A5129684247
FedReview: Review and Dispose Poisoned Updates Without Validation Datasets or Historic Knowledge
2026 · Tianhang Zheng, Yanlu Li, et al. · Lecture notes in computer science · 1
PDF
Poisoning with a Pill: Circumventing Detection in Federated Learning
2026 · Hanxi Guo, Hao Wang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 1
PDF
HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
2025 · Dong, Jiangwen, Li, Jiayu, et al. · arXiv (Cornell University) · 1
PDF
AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors
2024 · Zhao, Mengnan, Zhang, Lihe, et al. · arXiv (Cornell University) · 1
PDF
Separable Multi-Concept Erasure from Diffusion Models
2024 · Zhao, Mengnan, Zhang, Lihe, et al. · arXiv (Cornell University) · 1
PDF
ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety--Utility Co-Enhancement
2026 · Qi, Weiwei, Wang, Chongyu, et al. · arXiv (Cornell University)
PDF
JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills
2026 · Wen, Xiaoyu, Li, Jiajia, et al. · arXiv (Cornell University)
PDF
ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions
2026 · Huang, Xinzhe, Yao, Biwu, et al. · arXiv (Cornell University)
PDF
Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
2026 · Zhao, Mengnan, Min, Geyong, et al. · arXiv (Cornell University)
PDF
REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
2026 · Huang, Zhengze, Yu, Luyang, et al. · arXiv (Cornell University)
PDF
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
2026 · Zhao, Puning, Zhang, Zhikun, et al. · arXiv (Cornell University)
PDF
AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
2026 · Wang, Ruoyu, Zhao, Heng, et al. · arXiv (Cornell University)
PDF
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
2026 · Qi, Weiwei, Wu, Zefeng, et al. · arXiv (Cornell University)
PDF
TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
2026 · Zeng, Churui, Xiu, Kedong, et al. · arXiv (Cornell University)
PDF
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
2026 · Liu, Dongrui, Li, Yu, et al. · arXiv (Cornell University)
PDF
RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
2026 · Lv, Bo, Xu, Zhiheng, et al. · arXiv (Cornell University)
PDF
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
2026 · Li, Jianan, Qin, Simeng, et al. · arXiv (Cornell University)
PDF
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
2026 · Zhao, Mengnan, Zhang, Lihe, et al. · arXiv (Cornell University)
PDF
Mitigating Error Amplification in Fast Adversarial Training
2026 · Zhao, Mengnan, Zhang, Lihe, et al. · arXiv (Cornell University)
PDF
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
2026 · Qi, Weiwei, Wu, Zefeng, et al. · arXiv (Cornell University)
PDF
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
2026 · Weiwei Qi, Shuo Shao, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
Accelerating Suffix Jailbreak attacks with Prefix-Shared KV-cache
2026 · Wang, Xinhai, Fu, Shaopeng, et al. · arXiv (Cornell University)
PDF
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
2026 · Wen, Xiaoyu, He, Zhida, et al. · arXiv (Cornell University)
PDF
Poisoning with a Pill: Circumventing Detection in Federated Learning
2026 · Association for Artificial Intelligence 2026, Guan, Haibing, et al. · Underline Science Inc.
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
2026 · Association for Artificial Intelligence 2026, Gu, Wei, et al. · Underline Science Inc.
Works count: 28
Citation count: 5
H-index: 1
I10-index:
Year
Topic
Type