Search Results for author:
Found 12 papers, 5 papers with code
Intrusion Detection with Segmented Federated Learning for Large-Scale Multiple LANs
In this research, a segmented federated learning is proposed, different from a collaborative learning based on single global model in a traditional federated learning model, it keeps multiple global models which allow each segment of participants to conduct collaborative learning separately and rearranges the segmentation of participants dynamically as well.
Ranked #1 on
Network Intrusion Detection
on SIDD-Image
Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness
Wider coverage and a better solution to a latency reduction in 5G necessitate its combination with multi-access edge computing (MEC) technology.
Information Stealing in Federated Learning Systems Based on Generative Adversarial Networks
At last, we successfully reconstructed the real data of the victim from the shared global model parameters with all the applied datasets.
Homogeneous Learning: Self-Attention Decentralized Deep Learning
To this end, we propose a decentralized learning model called Homogeneous Learning (HL) for tackling non-IID data with a self-attention mechanism.
Federated Phish Bowl: LSTM-Based Decentralized Phishing Email Detection
We collected the most recent phishing samples to study the effectiveness of the proposed method using different client numbers and data distributions.
Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis
To overcome this challenge, we propose the Attacking Distance-aware Attack (ADA) to enhance a poisoning attack by finding the optimized target class in the feature space.
Ranked #1 on
Model Poisoning
on Fashion-MNIST
Feature Distribution Matching for Federated Domain Generalization
The empirical results show that FedKA achieves performance gains of 8. 8% and 3. 5% in Digit-Five and Office-Caltech10, respectively, and a gain of 0. 7% in Amazon Review with extremely limited training data.
Wireless Ad Hoc Federated Learning: A Fully Distributed Cooperative Machine Learning
WAFL can develop generalized models from Non-IID datasets stored in distributed nodes locally by exchanging and aggregating them with each other over opportunistic node-to-node contacts.
Bidirectional Contrastive Split Learning for Visual Question Answering
To this end, we propose Bidirectional Contrastive Split Learning (BiCSL) to train a global multi-modal model on the entire data distribution of decentralized clients.
Resilience of Wireless Ad Hoc Federated Learning against Model Poisoning Attacks
Compared to conventional federated learning, WAFL performs model training by weakly synchronizing the model parameters with others, and this shows great resilience to a poisoned model injected by an attacker.
Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space
To this end, we propose an instance-level multimodal Trojan attack on VQA that efficiently adapts to fine-tuned models through a dual-modality adversarial learning method.
Associative Transformer
Existing studies such as the Coordination method employ iterative cross-attention mechanisms with a bottleneck to enable the sparse association of inputs.
