Junfeng Guo

CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining

Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data

A Watermark for Order-Agnostic Language Models

De-mark: Watermark Removal in Large Language Models

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing

Pseudo- vs. True-Randomness: Rethinking Distortion-Free Watermarks of Language Models under Watermark Key Collisions

RAG$^C$: Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models