# AIGT detection on HC3 Deep-Word-Bug attack AI to Human (in-domain) Source: [AIGT detection on HC3 Deep-Word-Bug attack AI to Human (in-domain)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:24.870Z Evaluation of AI Generated Text (AIGT) detection performance using the HC3 dataset subset generated via the Deep-Word-Bug attack, specifically comparing AI outputs against human references in-domain. 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 | AIGT detection | | Dataset (including any stated split) | HC3 Deep-Word-Bug attack AI to Human (in-domain) | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Overall Accuracy](): Higher is better; unit: PERCENT. - [AUA Score](): Higher is better; unit: SCALAR. - [Attack Success Rate](): Higher is better; unit: PERCENT. - [ANQ Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BERT | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | RoBERTa | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | DeBERTa | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | Flooding | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | RanMASK | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | RMLM | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | SCRN | 100 | Not recorded | 68fa73e41e209131cea5eb76 | | SeqXGPT | 99.5 | Not recorded | 68fa73e41e209131cea5eb76 | | RDrop | 99.5 | Not recorded | 68fa73e41e209131cea5eb76 | | ChatGPT-Detector | 98 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Rank | 96.5 | Not recorded | 68fa73e41e209131cea5eb76 | | Log-Likelihood | 96 | Not recorded | 68fa73e41e209131cea5eb76 | | GLTR | 95 | Not recorded | 68fa73e41e209131cea5eb76 | | Entropy | 86 | Not recorded | 68fa73e41e209131cea5eb76 | ### BERT Overall Accuracy: 100. Result ID: 699311603a6c31484913771f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RoBERTa Overall Accuracy: 100. Result ID: 699311603a6c314849137720. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeBERTa Overall Accuracy: 100. Result ID: 699311603a6c314849137721. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Flooding Overall Accuracy: 100. Result ID: 699311603a6c314849137723. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RanMASK Overall Accuracy: 100. Result ID: 699311603a6c314849137725. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RMLM Overall Accuracy: 100. Result ID: 699311603a6c314849137726. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SCRN Overall Accuracy: 100. Result ID: 699311603a6c314849137727. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### SeqXGPT Overall Accuracy: 99.5. Result ID: 699311603a6c31484913771e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RDrop Overall Accuracy: 99.5. Result ID: 699311603a6c314849137724. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### ChatGPT-Detector Overall Accuracy: 98. Result ID: 699311603a6c314849137722. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Log-Rank Overall Accuracy: 96.5. Result ID: 699311603a6c31484913771b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Log-Likelihood Overall Accuracy: 96. Result ID: 699311603a6c31484913771a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLTR Overall Accuracy: 95. Result ID: 699311603a6c31484913771d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Entropy Overall Accuracy: 86. Result ID: 699311603a6c31484913771c. [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.