Zhan Qin
~Zhan_Qin2
13
论文总数
6.5
年均投稿
平均评分
接收情况5/13
会议分布
ICLR
10
NeurIPS
3
发表论文 (13 篇)
202511 篇
5
Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models
ICLR 2025withdrawn
4
Don’t Say No: Jailbreaking LLM by Suppressing Refusal
ICLR 2025withdrawn
4
WMCopier: Forging Invisible Watermarks on Arbitrary Images
NeurIPS 2025Poster
4
Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothing
ICLR 2025withdrawn
4
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
ICLR 2025Poster
4
Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
ICLR 2025Rejected
4
Structure-Aware Parameter-Efficient Machine Unlearning on Transformer Models
ICLR 2025Rejected
4
JudgeRail: Harnessing Open-Source LLMs for Fast Harmful Text Detection with Judicial Prompting and Logit Rectification
ICLR 2025Rejected
4
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
NeurIPS 2025Poster
5
A Comprehensive Deepfake Detector Assessment Platform
ICLR 2025Rejected
4
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
NeurIPS 2025Poster