Search Results for author:
Found 5 papers, 2 papers with code
Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption
In this paper, we present Pencil, the first private training framework for collaborative learning that simultaneously offers data privacy, model privacy, and extensibility to multiple data providers, without relying on the non-colluding assumption.
Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed
Many types of NNs (such as Recurrent Neural Network (RNN), and transformers) that are designed to work with sequential data have advantages over tree-based models, because they can take raw network data as input without complex feature computations on the fly.
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
According to the channel model, we propose algorithms to constrain the information transmitted in a single round of local training.
LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers
The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for inference.
A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
We also evaluate the effectiveness of our attack under two defenses: one is well-designed adversarial graph detector and the other is that the target GNN model itself is equipped with a defense to prevent adversarial graph generation.
