论文列表

• Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
• How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study
• 自然语言处理中的探针可解释方法综述
• Backdoor NLP Models via AI-Generated Text
• Multi-Grained Multimodal Interaction Network for Sentiment Analysis
• NWS: Natural Textual Backdoor Attacks via Word Substitution
• SDPSAT: Syntactic Dependency Parsing Structure-Guided Semi-Autoregressive Machine Translation
• Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts
• FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning
• DESC-IDS: Towards an Efficient Real-time Automotive Intrusion Detection System Based on Deep Evolving Stream Clustering
• A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
• Sense-aware BERT and Multi-task Fine-tuning for Multimodal Sentiment Analysis
• TIMS: A Novel Approach for Incrementally Few-Shot Text Instance Selection via Model Similarity
• PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning