# Layer-wise Selective Attack (LSA) Robustness on Federated Learning Dataset Source: [Layer-wise Selective Attack (LSA) Robustness on Federated Learning Dataset]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:58.107Z Evaluation of model robustness against Layer-wise Selective Attacks (LSA) within a 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 | Layer-wise Selective Attack (LSA) 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](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Multi-Krum | 90.58 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 90.44 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 87.81 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 86.73 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 82.23 | Not recorded | 699547c809c33900fcd6d726 | | Median | 79.61 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 78.09 | Not recorded | 699547c809c33900fcd6d726 | | Median | 77.91 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 76.89 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 76.63 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 76.56 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 73.86 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 73.34 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 72.19 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 69.98 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 64.83 | Not recorded | 699547c809c33900fcd6d726 | ### Multi-Krum Accuracy: 90.58. Result ID: 699aaa1d5698665ec43700d3. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Flame Accuracy: 90.44. Result ID: 699aaa1d5698665ec43700d5. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 87.81. Result ID: 699aaa1d5698665ec43700d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 86.73. Result ID: 699aaa1d5698665ec43700d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 82.23. Result ID: 699aaa1d5698665ec43700cf. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Median Accuracy: 79.61. Result ID: 699aaa1d5698665ec43700c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 78.09. Result ID: 699aaa1d5698665ec43700c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Median Accuracy: 77.91. Result ID: 699aaa1d5698665ec43700cd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 76.89. Result ID: 699aaa1d5698665ec43700c9. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 76.63. Result ID: 699aaa1d5698665ec43700ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 76.56. Result ID: 699aaa1d5698665ec43700cc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 73.86. Result ID: 699aaa1d5698665ec43700c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 73.34. Result ID: 699aaa1d5698665ec43700d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Flame Accuracy: 72.19. Result ID: 699aaa1d5698665ec43700cb. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 69.98. Result ID: 699aaa1d5698665ec43700ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 64.83. Result ID: 699aaa1d5698665ec43700d1. [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.