# BadNets Backdoor Attack Robustness on Federated Learning Dataset Source: [BadNets Backdoor Attack Robustness on Federated Learning Dataset]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:58.072Z Evaluation of model robustness against BadNets backdoor attacks within a Federated Learning setting. Key metrics include overall 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 | BadNets Backdoor Attack 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 | | --- | --- | --- | --- | | FLTrust | 89.51 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 88.28 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 87.78 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 87.31 | Not recorded | 699547c809c33900fcd6d726 | | Median | 79.26 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 79.11 | Not recorded | 699547c809c33900fcd6d726 | | Median | 78.91 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 78.89 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 78.13 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 77.58 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 76.04 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 75.72 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 75.1 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 74.49 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 62.91 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 58.93 | Not recorded | 699547c809c33900fcd6d726 | ### FLTrust Accuracy: 89.51. Result ID: 699aaa1d5698665ec43700b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 88.28. Result ID: 699aaa1d5698665ec43700b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Flame Accuracy: 87.78. Result ID: 699aaa1d5698665ec43700b5. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 87.31. Result ID: 699aaa1d5698665ec43700b3. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Median Accuracy: 79.26. Result ID: 699aaa1d5698665ec43700ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 79.11. Result ID: 699aaa1d5698665ec43700ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Median Accuracy: 78.91. Result ID: 699aaa1d5698665ec43700a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 78.89. Result ID: 699aaa1d5698665ec43700ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 78.13. Result ID: 699aaa1d5698665ec43700a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 77.58. Result ID: 699aaa1d5698665ec43700a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 76.04. Result ID: 699aaa1d5698665ec43700ab. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 75.72. Result ID: 699aaa1d5698665ec43700aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 75.1. Result ID: 699aaa1d5698665ec43700b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 74.49. Result ID: 699aaa1d5698665ec43700a9. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 62.91. Result ID: 699aaa1d5698665ec43700b1. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 58.93. Result ID: 699aaa1d5698665ec43700af. [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.