Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Federated Learning for Energy-balanced Client Selection in Mobile Edge ComputingPublication . Zheng, Jingjing; Li, Kai; Tovar, Eduardo; Guizani, MohsenMobile edge computing (MEC) has been considered as a promising technology to provide seamless integration of multiple application services. Federated learning (FL) is carried out at edge clients in MEC for privacy-preserving training of data processing models. Despite that the edge clients with small data payloads consume less energy on FL training, the small data payload gives rise to a low learning accuracy due to insufficient input to the FL training. Inadequate selection of the edge clients can result in a large energy consumption at the edge clients, or a low learning accuracy of the FL training. In this paper, a new FL-based client selection optimization is proposed to balance the trade-off between energy consumption of the edge clients and the learning accuracy of FL. We first show that this optimization problem is NP-complete. Next, we propose a FL-based energy-accuracy balancing heuristic algorithm to approximate the optimal client selection in polynomial time. The numerical results show the advantage of our proposed algorithm.
- Leverage variational graph representation for model poisoning on federated learningPublication . Li, Kai; Yuan, Xin; Zheng, Jingjing; Ni, Wei; Dressler, Falko; Jamalipour, AbbasThis article puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models’ features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL.
- Poisoning federated learning with graph neural networks in Internet of DronesPublication . Li, Kai; NOOR, ALAM; Ni, Wei; Tovar, Eduardo; Fu, Xiaoming; Akan, Ozgur B.Internet of Drones (IoD) is an innovative technology that integrates mobile computing capabilities with drones, enabling them to process data at or near the location where it is collected. Federated learning can significantly enhance the efficiency and effectiveness of data processing and decision-making in IoD. Since federated learning relies on aggregating updates from multiple drones, a malicious drone can generate poisoning local model updates that involves erroneous information, leading to incorrect decisions or even dangerous situations. In this paper, a new data-independent model poisoning attack is developed to manipulate federated learning accuracy, which does not rely on training data at drones. The proposed attack leverages an adversarial graph neural network (A-GNN) to generate poisoning local model updates based on the benign local models overheard. Particularly, the A-GNN discerns the graph structural correlations between the benign local models and the features of the training data that underpin these models. The graph structural correlations are reconstructively manipulated at the malicious drone to crafts poisoning local model updates, where the training loss of the federated learning is maximized.
- Exploring Deep Reinforcement Learning- Assisted Federated Learning for Online Resource Allocation in Privacy-Preserving EdgeIoTPublication . Zheng, Jingjing; Li, Kai; Ni, Wei; Tovar, Eduardo; Guizani, Mohsen; Mhaisen, NaramFederated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT). On the one hand, the learning accuracy of FL can be improved by selecting the IoT devices with large datasets for training, which gives rise to a higher energy consumption. On the other hand, the energy consumption can be reduced by selecting the IoT devices with small datasets for FL, resulting in a falling learning accuracy. In this paper, we formulate a new resource allocation problem for privacy-preserving EdgeIoT to balance the learning accuracy of FL and the energy consumption of the IoT device. We propose a new federated learning-enabled twin-delayed deep deterministic policy gradient (FLDLT3) framework to achieve the optimal accuracy and energy balance in a continuous domain. Furthermore, long short term memory (LSTM) is leveraged in FL-DLT3 to predict the time-varying network state while FL-DLT3 is trained to select the IoT devices and allocate the transmit power. Numerical results demonstrate that the proposed FL-DLT3 achieves fast convergence (less than 100 iterations) while the FL accuracy-to-energy consumption ratio is improved by 51.8% compared to existing state-of-the-art benchmark.