Search Results for author:
Found 7 papers, 1 papers with code
Topic-based Watermarks for LLM-Generated Text
In this work, focusing on the limitations of current watermarking schemes, we propose the concept of a "topic-based watermarking algorithm" for LLMs.
Protecting Sensitive Data through Federated Co-Training
Federated learning allows us to collaboratively train a model without pooling the data by iteratively aggregating the parameters of local models.
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against White-Box Models
We have evaluated the performance of AUTOLYCUS on 5 machine learning datasets, in terms of the surrogate model's accuracy and its similarity to the target model.
GenShare: Sharing Accurate Differentially-Private Statistics for Genomic Datasets with Dependent Tuples
While sharing genomic data across researchers is an essential driver of advances in health and biomedical research, the sharing process is often infeasible due to data privacy concerns.
The Curse of Correlations for Robust Fingerprinting of Relational Databases
Database fingerprinting have been widely adopted to prevent unauthorized sharing of data and identify the source of data leakages.
Cryptography and Security Databases
Key Protected Classification for Collaborative Learning
Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners.
Key Protected Classification for GAN Attack Resilient Collaborative Learning
To the best of our knowledge, the proposed approach is the first collaborative learning formulation that effectively tackles an active adversary, and, unlike model corruption or differential privacy formulations, our approach does not inherently feature a trade-off between model accuracy and data privacy.
