8 papers
When Sample Selection Bias Precipitates Model Collapse
Xinbao Qiao, Xianglong Du, Wei Liu +4
The proliferation of recursive training on synthetic data can alleviate data scarcity but risks model collapse, where repeated training erodes distributional tails and homogenizes…
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
Peihua Mai, Xuanrong Gao, Youlong Ding +3
With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue. Existing privacy-pr…
MRMMIA: Membership Inference Attacks on Memory in Chat Agents
Kai Chen, Yan Pang, Tianhao Wang
Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine lear…
ConfusionPrompt: Practical Private Inference for Online Large Language Models
Peihua Mai, Youjia Yang, Ran Yan +2
State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant priv…
As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files
Haodong Li, Jingqi Zhang, Xiao Cheng +3
The remarkable language ability of Large Language Models (LLMs) stems from extensive training on vast datasets, often including copyrighted material, which raises serious concerns…
Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
Jingqi Zhang, Ruibo Chen, Yingqing Yang +3
Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrig…