# Skill Poisoning Detection on MASW Source: [Skill Poisoning Detection on MASW]() Collection index: [llms.txt]() Data updated: 2026-04-28T07:10:13.898Z Evaluation of model performance for detecting skill poisoning attacks using the MASW dataset, measured by Precision, Recall, and F1 Score. 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 | Skill Poisoning Detection | | Dataset (including any stated split) | MASW | | Metric | Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | 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 - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision | Result date | Report paper | | --- | --- | --- | --- | | MSkills | 73.67 | Not recorded | 69f03f0e55a3c32af89fa002 | | RouteGuard | 63.93 | Not recorded | 69f03f0e55a3c32af89fa002 | | Scan | 60 | Not recorded | 69f03f0e55a3c32af89fa002 | | MWild | 58.76 | Not recorded | 69f03f0e55a3c32af89fa002 | | Malicious Or Not | 56.73 | Not recorded | 69f03f0e55a3c32af89fa002 | | Wild | 41.43 | Not recorded | 69f03f0e55a3c32af89fa002 | | Probe | 36.33 | Not recorded | 69f03f0e55a3c32af89fa002 | | Inj | 36.12 | Not recorded | 69f03f0e55a3c32af89fa002 | ### MSkills Precision: 73.67. Result ID: 69f05d4b47f34ce924d5bebe. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RouteGuard Precision: 63.93. Result ID: 69f05d4b47f34ce924d5bebf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Scan Precision: 60. Result ID: 69f05d4b47f34ce924d5beb9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MWild Precision: 58.76. Result ID: 69f05d4b47f34ce924d5bebb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Malicious Or Not Precision: 56.73. Result ID: 69f05d4b47f34ce924d5bebc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Wild Precision: 41.43. Result ID: 69f05d4b47f34ce924d5beba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Probe Precision: 36.33. Result ID: 69f05d4b47f34ce924d5bebd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Inj Precision: 36.12. Result ID: 69f05d4b47f34ce924d5beb8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.