7 papers
Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning
Shiyu Miao, Yunlong Mao, Zirui Huang +5
Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface is a faithful derivative of…
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Zirui Huang, Yunlong Mao, Wei Tong +3
The proliferation of customized Large Language Models (LLMs) poses critical risks of Data Intellectual Property (Data IP) infringement via unauthorized fine-tuning on proprietary d…
Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
Zi Li, Tian Zhou, Wenze Li +3
Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline fine-tuning'' is often viewed…
Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)
Yu Lin, Qizhi Zhang, Wenqiang Ruan +6
The rapid development of large language models (LLMs) has driven the widespread adoption of cloud-based LLM inference services, while also bringing prominent privacy risks associat…
On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
Zijian Wang, Wei Tong, Tingxuan Han +4
Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-…
SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning
Chengcheng Zhu, Ye Li, Bosen Rao +3
Federated Learning (FL) has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenge…