# How To Backdoor Federated Learning Source: [How To Backdoor Federated Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:43:30.383Z Authors: Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov Published: 2018-07-02T04:37:43.000Z ## Abstract Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards without revealing what individual users type. We demonstrate that any participant in federated learning can introduce hidden backdoor functionality into the joint global model, e.g., to ensure that an image classifier assigns an attacker-chosen label to images with certain features, or that a word predictor completes certain sentences with an attacker-chosen word. We design and evaluate a new model-poisoning methodology based on model replacement. An attacker selected in a single round of federated learning can cause the global model to immediately reach 100% accuracy on the backdoor task. We evaluate the attack under different assumptions for the standard federated-learning tasks and show that it greatly outperforms data poisoning. Our generic constrain-and-scale technique also evades anomaly detection-based defenses by incorporating the evasion into the attacker's loss function during training. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Hair Color Classification on CelebA](): Hair color classification; CelebA; Accuracy: 91.3. - [Traffic Sign Recognition on GTSRB](): Traffic Sign Recognition; GTSRB; Accuracy: 98.8. ## Original sources and implementation [Original paper]() [PDF]()