Get started
Author

Kui Ren

Observed name: Ren, Kui
ORCID: 0000-0002-1969-2591
Observed ORCIDs: 0000-0002-1969-2591, 0000-0003-3441-6277
OpenAlex ID: A5121598261
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
2026 · Qi, Weiwei, Wu, Zefeng, et al. · arXiv (Cornell University) · 10
PDF
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving
2026 · Yan, Jianxin, Ni, Wangze, et al. · arXiv (Cornell University) · 6
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) · 3
PDF
Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution
2024 · Kuang, Peng, Wang, Zhibo, et al. · arXiv (Cornell University) · 3
PDF
LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
2026 · Wang, Yaopeng, Wang, Qingliang, et al. · arXiv (Cornell University) · 2
PDF
LoopTrap: Termination Poisoning Attacks on LLM Agents
2026 · Xu, Huiyu, Wang, Zhibo, et al. · arXiv (Cornell University) · 2
PDF
HintPilot: LLM-based Compiler Hint Synthesis for Code Optimization
2026 · Jiang, Hanyun, Yao, Peisen, et al. · arXiv (Cornell University) · 2
PDF
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
2026 · Zheng, Haolun, He, Yu, et al. · arXiv (Cornell University) · 2
PDF
When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
2026 · Shuai, Chao, Fan, Shaojing, et al. · arXiv (Cornell University) · 2
PDF
Towards Evaluation for Real-World LLM Unlearning
2025 · Miao, Ke, Hu, Yuke, et al. · arXiv (Cornell University) · 2
PDF
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models
2026 · Liu, Qirui, Sun, Yichen, et al. · arXiv (Cornell University) · 1
PDF
Ghosts Beneath Textures: Texture-Relation Cues for Cross-Paradigm AI-Generated Image Detection
2026 · Wang, Haoyu, Qin, Yiming, et al. · arXiv (Cornell University) · 1
PDF
ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM Guardrails
2026 · Wang, Yan, Chu, Zhixuan, et al. · arXiv (Cornell University) · 1
PDF
QCFuse: Query-Centric Cache Fusion for Efficient RAG Inference
2026 · Yan, Jianxin, Qian, Zeheng, et al. · arXiv (Cornell University) · 1
PDF
FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
2026 · An, Xinyuan, Luo, Tao, et al. · arXiv (Cornell University) · 1
PDF
STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
2026 · Wang, Kun, Chen, Meng, et al. · arXiv (Cornell University) · 1
PDF
Divide and Conquer: Multimodal Video Deepfake Detection via Cross-Modal Fusion and Localization
2026 · Li, Qingcao, He, Miao, et al. · arXiv (Cornell University) · 1
PDF
Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
2026 · Pan, Licheng, Yang, Haocheng, et al. · arXiv (Cornell University)
PDF
Improving Learning of Green's Functions Through Kernel Decomposition
2026 · Chen, Beiji, Du, Qiang, et al. · arXiv (Cornell University)
PDF
Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection
2026 · Miao He, Peng Cheng, et al. · Interspeech (USB)
PDF
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
2026 · Yao, Hongwei, Liu, Yiming, et al. · arXiv (Cornell University)
PDF
From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
2026 · Mou, Zhiyi, Ni, Wangze, et al. · arXiv (Cornell University)
PDF
Rethinking Practical Adversarial Example Attack on Speaker Recognition in Physical Domain
2026 · Qianniu Chen, Li Lu, et al. · IEEE Transactions on Mobile Computing
SJBP: A Platform to Launch a Novel Jailbreak Attack on Large Language Models Based on Content's Spatial Distribution
2026 · Zhiyi Mou, Zeheng Qian, et al. · International World Wide Web Conference (WWW)
"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
2026 · Zhang, Xinyu, Dong, Ziping, et al. · arXiv (Cornell University)
PDF
Works count: 35
Citation count: 44
H-index: 3
I10-index: 1
Year
Topic
Type