Xuandong Zhao

WatermarkAttacker. [NeurIPS 2024] Invisible Image Watermarks Are Provably Removable Using Generative AI

weak-to-strong. [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models

PRC-Watermark. [ICLR 2025] An Undetectable Watermark for Generative Image Models

Unigram-Watermark. [ICLR 2024] Provable Robust Watermarking for AI-Generated Text

pf-decoding. [ICLR 2025] Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs

DRW. [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP

Ginsew. [ICML 2023] Protecting Language Generation Models via Invisible Watermarking

NPPrompt. [ACL 2023] NPPrompt: Pre-trained Language Models Can be Fully Zero-Shot Learners

HPD. [ACL 2022] Homomorphic projective distillation (HPD) for sentence embedding

DVGCN. [ISBI 2019] Deep Voxel-Graph Convolution Network

CRT. [NAACL 2022] Confidentially Redacted Training (CRT)

awesome-rl. Reinforcement learning resources curated

Awesome-LLM-Watermark. UP-TO-DATE Watermark papers. 🔥🔥🔥

llm-watermark-location. Python

bm3d_experiments. Python

bm3d_src. C++

CGProject. C++

ComputerNetwork. C++

DigitalLogicDesign. C

ComputerOrganization. Verilog

ComputerArchitecture. Experiments writen in verilog