 Differentially Private Next-Token Prediction of Large Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 |
 ProMark: Proactive Diffusion Watermarking for Causal AttributionComputer Vision and Pattern Recognition (CVPR), 2024 |
 PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy
TrapsConference on Computer and Communications Security (CCS), 2024 |
 Efficiently Computing Similarities to Private DatasetsInternational Conference on Learning Representations (ICLR), 2024 |
 Do LLMs Dream of Ontologies?ACM Transactions on Intelligent Systems and Technology (ACM TIST), 2024 |
 Exploring Musical Roots: Applying Audio Embeddings to Empower Influence
Attribution for a Generative Music ModelInternational Society for Music Information Retrieval Conference (ISMIR), 2024 |
 Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable
Stress DetectionItalian National Conference on Sensors (INS), 2024 |
 Red Teaming Visual Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Privacy Preserving Adaptive Experiment DesignInternational Conference on Machine Learning (ICML), 2024 |
