# Distributed Backdoor Attack (DBA) Robustness on Federated Learning Dataset Source: [Distributed Backdoor Attack (DBA) Robustness on Federated Learning Dataset]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:58.054Z Evaluation of model robustness against Distributed Backdoor Attacks (DBA) within a general Federated Learning environment, reporting Accuracy (ACC) and Backdoor Success Rate (BSR). 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. | Scope | Recorded value | | --- | --- | | Task | Distributed Backdoor Attack (DBA) Robustness | | Dataset (including any stated split) | Federated Learning Dataset | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [Backdoor Success Rate (BSR)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Multi-Krum | 97.58 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 89.31 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 87.95 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 87.89 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 80.44 | Not recorded | 699547c809c33900fcd6d726 | | Median | 80.13 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 78.97 | Not recorded | 699547c809c33900fcd6d726 | | Median | 78.87 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 78.34 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 77.99 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 77.51 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 75.27 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 75.11 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 73.02 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 64.81 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 63.3 | Not recorded | 699547c809c33900fcd6d726 | ### Multi-Krum Accuracy: 97.58. Result ID: 699aaa1d5698665ec43700a3. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 89.31. Result ID: 699aaa1d5698665ec43700a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 87.95. Result ID: 699aaa1d5698665ec43700a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Flame Accuracy: 87.89. Result ID: 699aaa1d5698665ec43700a5. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 80.44. Result ID: 699aaa1d5698665ec437009e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Median Accuracy: 80.13. Result ID: 699aaa1d5698665ec437009d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 78.97. Result ID: 699aaa1d5698665ec437009c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Median Accuracy: 78.87. Result ID: 699aaa1d5698665ec4370097. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 78.34. Result ID: 699aaa1d5698665ec4370098. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 77.99. Result ID: 699aaa1d5698665ec4370096. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 77.51. Result ID: 699aaa1d5698665ec437009a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 75.27. Result ID: 699aaa1d5698665ec437009b. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 75.11. Result ID: 699aaa1d5698665ec43700a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 73.02. Result ID: 699aaa1d5698665ec4370099. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 64.81. Result ID: 699aaa1d5698665ec437009f. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Flame Accuracy: 63.3. Result ID: 699aaa1d5698665ec43700a1. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.