SISS Defense Protocol - Attack Success: leaderboard
SISS measures changes in hidden-text recovery between native and aggressively downsampled images. That cross-scale shift is distinct from a web agent taking an attacker-directed action. Main, web-agent and defense experiments use separate protocols; conditional remaining attack success uses the publisher’s paired counts. This board reports defended attack success rate (%). Lower is better.
Metric: Defended attack success rate (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 7 models tracked. Updated 14 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-VL-7B-Instruct (Harness: SISS defense ScaleGuard (adaptive)) | 15 | |
| 2 | Qwen2.5-VL-7B-Instruct (Harness: SISS defense ScaleGuard (non-adaptive)) | 24.3 | |
| 3 | Qwen 2.5 VL 7B Instruct (Harness: SISS defense Area resampling) | 67 | |
| 4 | Qwen 2.5 VL 7B Instruct (Harness: SISS defense Median reconstruction) | 67 | |
| 5 | Qwen 2.5 VL 7B Instruct (Harness: SISS defense Gaussian low-pass) | 67 | |
| 6 | Qwen2.5-VL-7B-Instruct (Harness: SISS defense Randomized masking (5 reps.)) | 68 | |
| 7 | Qwen2.5-VL-7B-Instruct (Harness: SISS defense JPEG(75) + + area) | 69 |
Interactive version: theaggregate.ai/benchmark?slug=siss-defense-protocol-attack-success · How It Works · Data refreshed daily, snapshot 2026-11-16.