Update README.md

README.md

@@ -90,18 +90,10 @@ We evaluate the model’s effectiveness in detecting Jailbreak, Goal Hijacking,
 
 #### Subdivision Scenarios
 
-![fig_3](C:\Users\17391\Desktop\gitbox\jailbreaking-llms.github.io-main\jailbreaking-llms.github.io-main\static\images\fig_3.png)
+![fig_3](./images/heatmap.svg)
 
 
 # Citation
 ```
-<!-- @misc{dubey2024llama3herdmodels,
-  title =         {The Llama 3 Herd of Models},
-  author =        {Llama Team, AI @ Meta},
-  year =          {2024}
-  eprint =        {2407.21783},
-  archivePrefix = {arXiv},
-  primaryClass =  {cs.AI},
-  url =           {https://arxiv.org/abs/2407.21783}
-} -->
+
 ```