5 papers
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Kejia Zhang, Tianyuan Zou, Zixuan GU +1
Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typical…
Position: Life-Logging Video Streams Make the Privacy-Utility Trade-off Inevitable
Tianyuan Zou, Liang Yue, Yang Liu +2
With the growing prevalence of always-on hardware such as smart glasses, body cameras, and home security systems, life-logging visual sensing is becoming inevitable, forming the ba…
Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Yang Liu, Kejia Zhang, Bingjie Yan +11
Large language models (LMs) offer broad generalization capabilities but require vast amounts of data and computational resources for domain-specific tasks; small models (SMs), in c…
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
Tianyuan Zou, Yang Liu, Peng Li +6
Substantial quantity and high quality are the golden rules of making a good training dataset with sample privacy protection equally important. Generating synthetic samples that res…
FuseGen: PLM Fusion for Data-generation based Zero-shot Learning
Tianyuan Zou, Yang Liu, Peng Li +3
Data generation-based zero-shot learning, although effective in training Small Task-specific Models (STMs) via synthetic datasets generated by Pre-trained Language Models (PLMs), i…