5 papers · 1 filter
FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
Su Zhang, Junfeng Guo, Heng Huang
Watermark radioactivity testing type of methods can detect whether a model was trained on watermarked documents, and have become key tools for protecting data ownership in the fine…
Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning
Junfeng Guo, Yiming Li, Ruibo Chen +4
Large language models (LLMs) are increasingly integrated into real-world personalized applications through retrieval-augmented generation (RAG) mechanisms to supplement their respo…
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
Mingyan Zhu, Yiming Li, Junfeng Guo +3
Currently, sample-specific backdoor attacks (SSBAs) are the most advanced and malicious methods since they can easily circumvent most of the current backdoor defenses. In this pape…
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
Yihan Wu, Zhengmian Hu, Junfeng Guo +2
Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge i…
Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
Yihan Wu, Ruibo Chen, Zhengmian Hu +4
Language model (LM) watermarking techniques inject a statistical signal into LM-generated content by substituting the random sampling process with pseudo-random sampling, using wat…