论文列表

• How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
• Backdoor NLP Models via AI-Generated Text
• 《动手学大模型》系列编程实践教程
• Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond
• NWS: Natural Textual Backdoor Attacks via Word Substitution
• FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning
• A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
• PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning