Stealthiness Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1.99Mean Perplexity
10
May 18, 2026
2.75Mean Perplexity (PPL)
10
May 18, 2026
2.78Mean PPL
10
May 18, 2026
2.33Mean Perplexity
10
May 18, 2026
2.16Mean PPL
10
May 18, 2026
2.34PPL Mean
10
May 18, 2026
3.05Mean Perplexity (PPL)
10
May 18, 2026
3.23Mean Perplexity
10
May 18, 2026
23.81Dual-Goal Success Rate
7
May 12, 2026
47.62Dual-Goal Success Rate
7
May 12, 2026
8,321Detected Samples
3
Feb 26, 2026
0.987SSIM
2
Feb 26, 2026