LFighter: Defending against the label-flipping attack in federated learning.

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for malicious peers to poison the model by conducting either untargeted or targeted poisoning attacks. The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i.e., the source class) to another (i.e., the target class). Unfortunately, this attack is easy to perform and hard to detect, and it negatively impacts the performance of the global model. Existing defenses against LF are limited by assumptions on the distribution of the peers' data and/or do not perform well with high-dimensional models. In this paper, we deeply investigate the LF attack behavior. We find that the contradicting objectives of attackers and honest peers on the source class examples are reflected on the parameter gradients corresponding to the neurons of the source and target classes in the output layer. This makes those gradients good discriminative features for the attack detection. Accordingly, we propose LFighter, a novel defense against the LF attack that first dynamically extracts those gradients from the peers' local updates and then clusters the extracted gradients, analyzes the resulting clusters, and filters out potential bad updates before model aggregation. Extensive empirical analysis on three data sets shows the effectiveness of the proposed defense regardless of the data distribution or model dimensionality. Also, LFighter outperforms several state-of-the-art defenses by offering lower test error, higher overall accuracy, higher source class accuracy, lower attack success rate, and higher stability of the source class accuracy. Our code and data are available for reproducibility purposes at https://github.com/NajeebJebreel/LFighter.

Enhanced Security and Privacy via Fragmented Federated Learning.

In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconciling accuracy with privacy and security is a challenge to FL. On the one hand, good updates sent by honest participants may reveal their private local information, whereas poisoned updates sent by malicious participants may compromise the model's availability and/or integrity. On the other hand, enhancing privacy via update distortion damages accuracy, whereas doing so via update aggregation damages security because it does not allow the server to filter out individual poisoned updates. To tackle the accuracy-privacy-security conflict, we propose fragmented FL (FFL), in which participants randomly exchange and mix fragments of their updates before sending them to the server. To achieve privacy, we design a lightweight protocol that allows participants to privately exchange and mix encrypted fragments of their updates so that the server can neither obtain individual updates nor link them to their originators. To achieve security, we design a reputation-based defense tailored for FFL that builds trust in participants and their mixed updates based on the quality of the fragments they exchange and the mixed updates they send. Since the exchanged fragments' parameters keep their original coordinates and attackers can be neutralized, the server can correctly reconstruct a global model from the received mixed updates without accuracy loss. Experiments on four real data sets show that FFL can prevent semi-honest servers from mounting privacy attacks, can effectively counter-poisoning attacks, and can keep the accuracy of the global model.