Card: add Figure 1 and comparison bar chart

README.md

@@ -26,6 +26,9 @@ categories.
 
 ## How it works
 
+<p align="center"><img src="https://huggingface.co/EuroSafeAI/EuroSafeGuard-v1/resolve/main/assets/overview.png" width="900" alt="EuroSafeGuard pipeline"></p>
+<p align="center"><img src="https://huggingface.co/EuroSafeAI/EuroSafeGuard-v1/resolve/main/assets/example.png" width="900" alt="Jailbreak answered without a guard, blocked with EuroSafeGuard"></p>
+
 1. **Probe.** An MLP probe on Llama-3.1-8B-Instruct activations scores every request; the top 10% (by WildChat-clean) are escalated.
 2. **Input and exchange classifiers.** Escalated requests are scored by an input classifier and, after the model replies, by an exchange classifier that reads prompt and reply (Qwen3.5-9B + LoRA + 11 heads each).
 3. **Decision.** The reply is blocked if `0.6·probe_z + 0.2·input_z + 0.2·exchange_z` exceeds a calibrated threshold.
@@ -51,6 +54,8 @@ otherwise answered under a policy note (`guard.system_note(category)`).
 
 ## Results
 
+<p align="center"><img src="https://huggingface.co/EuroSafeAI/EuroSafeGuard-v1/resolve/main/assets/bars.png" width="720" alt="Mean robustness over six attack sets vs 16 open guards"></p>
+
 Input stage, every guard at 5% of WildChat-clean flagged (recall %, ↑; PAIR/TAP: % of behaviors broken, ↓):
 
 | Guard | PyRIT | BELLS-O jb | BET | GB×JF | PAIR | TAP |