4 papers
Reverse-Engineering Model Editing on Language Models
Zhiyu Sun, Minrui Luo, Yu Wang +2
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a main…
Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
Wenjie Li, Siying Gu, Yiming Li +4
Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to…
FOBNN: Fast Oblivious Inference via Binarized Neural Networks
Xin Chen, Zhili Chen, Shiwen Wei +2
The remarkable performance of deep learning has sparked the rise of Deep Learning as a Service (DLaaS), allowing clients to send their personal data to service providers for model…
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
Benchang Dong, Zhili Chen, Xin Chen +3
Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with…