# Layer-wise Poisoning Attack (LPA) Robustness on Federated Learning Dataset Source: [Layer-wise Poisoning Attack (LPA) Robustness on Federated Learning Dataset]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:58.089Z Evaluation of model robustness against Layer-wise Poisoning Attacks (LPA) within a Federated Learning context, 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 Poisoning Attack (LPA) 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 | 90.48 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 90.37 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 90.16 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 89.29 | Not recorded | 699547c809c33900fcd6d726 | | Median | 78.63 | Not recorded | 699547c809c33900fcd6d726 | | Median | 78.3 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 77.66 | Not recorded | 699547c809c33900fcd6d726 | | Trimmed-Mean | 76.18 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 75.9 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 74.01 | Not recorded | 699547c809c33900fcd6d726 | | FedAVG | 72.97 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 69.37 | Not recorded | 699547c809c33900fcd6d726 | | Multi-Krum | 68.45 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 68.3 | Not recorded | 699547c809c33900fcd6d726 | | Flame | 66.51 | Not recorded | 699547c809c33900fcd6d726 | | FLTrust | 64.95 | Not recorded | 699547c809c33900fcd6d726 | ### Multi-Krum Accuracy: 90.48. Result ID: 699aaa1d5698665ec43700c3. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Flame Accuracy: 90.37. Result ID: 699aaa1d5698665ec43700c5. [Reporting paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 90.16. Result ID: 699aaa1d5698665ec43700c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 89.29. Result ID: 699aaa1d5698665ec43700c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"CNN"}. This record does not assert independent reproduction. ### Median Accuracy: 78.63. Result ID: 699aaa1d5698665ec43700bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Median Accuracy: 78.3. Result ID: 699aaa1d5698665ec43700b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 77.66. Result ID: 699aaa1d5698665ec43700be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Trimmed-Mean Accuracy: 76.18. Result ID: 699aaa1d5698665ec43700b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 75.9. Result ID: 699aaa1d5698665ec43700bc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 74.01. Result ID: 699aaa1d5698665ec43700c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FedAVG Accuracy: 72.97. Result ID: 699aaa1d5698665ec43700b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 69.37. Result ID: 699aaa1d5698665ec43700bf. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### Multi-Krum Accuracy: 68.45. Result ID: 699aaa1d5698665ec43700b9. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 68.3. Result ID: 699aaa1d5698665ec43700bb. [Reporting paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. ### Flame Accuracy: 66.51. Result ID: 699aaa1d5698665ec43700c1. [Reporting paper]() Recorded evaluation configuration: {"Model":"VGG19"}. This record does not assert independent reproduction. ### FLTrust Accuracy: 64.95. Result ID: 699aaa1d5698665ec43700ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"ResNet18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.