科研成果

吴宗儒, 张倬胜, 程彭洲, 刘功申 (2024). Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space. In ACL2024.

陆千禧, 何怡, 王士林 (2024). Personatalk: Preserving Personalized Dynamic Speech Style in Talking Face Generation. In ICIP 2024.

何怡, 杨磊, 王士林 (2024). Lip Feature Disentanglement for Visual Speaker Authentication in Natural Scenes. In IEEE TCSVT.

PDF Cite 代码 DOI

鞠天杰, 杜巍, 刘功申 (2024). How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study. In COLING.

鞠天杰, 刘功申, 张倬胜 (2024). 自然语言处理中的探针可解释方法综述. In 计算机学报.

杜巍, 鞠天杰, 刘功申 (2024). Backdoor NLP Models via AI-Generated Text. In COLING.

方岭永, 刘功申 (2024). Multi-Grained Multimodal Interaction Network for Sentiment Analysis. In ICASSP 2024.

何怡, 杨磊, 王晗亦, 王士林 (2024). Speaker-Adaptive Lipreading via Spatio-Temporal Information Learning. In ICASSP 2024.

闫超博, 李方圻, 王士林 (2024). Data-Free Watermark for Deep Neural Networks by Truncated Adversarial Distillation. In ICASSP 2024.

李方圻, 赵皓东, 杜巍, 王士林 (2024). Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond. In AAAI 2024.

杜巍, 袁童鑫, 赵皓东, 刘功申 (2023). NWS: Natural Textual Backdoor Attacks via Word Substitution. In ICASSP.

陈欣然, 赵彧然, 郭建铭, 段苏峰, 刘功申 (2023). SDPSAT: Syntactic Dependency Parsing Structure-Guided Semi-Autoregressive Machine Translation. In ICONIP.

杨磊, 王士林 (2023). Fine-Grained Lip Image Segmentation using Fuzzy Logic and Graph Reasoning. In IEEE TFS.

鞠天杰, 王晗亦, 赵皓东, 刘功申 (2023). Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts. In ACL.

李方圻, 王士林 (2023). Measure and Countermeasure of the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks. In ICASSP 2023.

赵皓东, 杜巍, 李方圻, 李珮玄, 刘功申 (2023). FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning. In ICASSP 2023.

郭子豪, 王士林 (2023). Content-Insensitive Dynamic Lip Feature Extraction for Visual Speaker Authentication against Deepfake Attacks. In ICASSP 2023.

张凯旋, 刘子涵, 胡嘉尚, 王士林 (2023). An Auto-Encoder Based Method for Camera Fingerprint Compression. In ICASSP 2023.

李方圻, 王士林 (2023). Linear Functionality Equivalence Attack against Deep Neural Network Watermarks and a Defense Method by Neuron Mapping. In IEEE TIFS.

王晗亦, 刘子涵, 王士林 (2023). Exploiting Complementary Dynamic Incoherence for DeepFake Video Detection. In TCSVT 2023.

刘子涵, 王晗亦, 王士林 (2022). Cross-Domain Local Characteristic Enhanced Deepfake Video Detection. In ACCV 2022.

程彭洲, 刘功申 (2022). DESC-IDS: Towards an Efficient Real-time Automotive Intrusion Detection System Based on Deep Evolving Stream Clustering. In FGCS.

赵皓东, 杜巍, 郭俊杰, 刘功申 (2022). A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network. In Interspeech 2022.

方岭永, 刘功申 (2022). Sense-aware BERT and Multi-task Fine-tuning for Multimodal Sentiment Analysis. In IJCNN 2022.

鞠天杰, 刘功申 (2022). TIMS: A Novel Approach for Incrementally Few-Shot Text Instance Selection via Model Similarity. In IJCNN.

杜巍, 赵易淳, 王世林, 刘功申 (2022). PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning. In IJCAI.

李方圻, 王士林 (2022). Online Intrusion Detection for IoT Systems with Full Bayesian Possibilistic Clustering and Ensembled Fuzzy Classifiers. In IEEE TFS.