Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Standard Harmful Content Datasets

Benchmarks

Task NameDataset NameSOTA ResultTrend
Harmful Content DetectionStandard Harmful Content Datasets Evasion Attack
Phishing96
3
Harmful Content DetectionStandard Harmful Content Datasets (Goal Hijacking Attack)
Phishing96
2
Harmful Content DetectionStandard Harmful Content Datasets Misdirection Attack
Phishing97
2
Showing 3 of 3 rows