Search Results for author:
Found 9 papers, 6 papers with code
Practical Blind Membership Inference Attack via Differential Comparisons
The success of the former heavily depends on the quality of the shadow model, i. e., the transferability between the shadow and the target; the latter, given only blackbox probing access to the target model, cannot make an effective inference of unknowns, compared with MI attacks using shadow models, due to the insufficient number of qualified samples labeled with ground truth membership information.
MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs
We test our model on several graph datasets including directed homogeneous and heterogeneous graphs.
CDGNet: A Cross-Time Dynamic Graph-based Deep Learning Model for Traffic Forecasting
Besides, we propose a novel encoder-decoder architecture to incorporate the cross-time dynamic graph-based GCN for multi-step traffic forecasting.
RFID-Based Indoor Spatial Query Evaluation with Bayesian Filtering Techniques
Based on the inference method and tracking models, we develop innovative indoor range and k nearest neighbor (kNN) query algorithms.
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Federated learning (FL) allows multiple clients to collaboratively train a deep learning model.
Rethinking Graph Lottery Tickets: Graph Sparsity Matters
Therefore, we propose two techniques to improve GNN performance when the graph sparsity is high.
SneakyPrompt: Jailbreaking Text-to-image Generative Models
Text-to-image generative models such as Stable Diffusion and DALL$\cdot$E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones.
Successfully Applying Lottery Ticket Hypothesis to Diffusion Model
Therefore, we propose to find the winning ticket with varying sparsity along different layers in the model.
A Survey of Lottery Ticket Hypothesis
The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i. e., winning tickets) that can achieve even better performance than the original model when trained in isolation.
