RomanNum3ral
/
cai
mirror of https://github.com/aliasrobotics/cai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

minor improvements in docs 

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>
This commit is contained in:
Víctor Mayoral Vilches 2025-11-02 14:24:16 +00:00
parent f5f3c42eb5
commit fde4c4aef4
5 changed files with 53 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/benchmarking/attack_defense.md
View File

@ -33,7 +33,7 @@ In rigorous Attack & Defense CTF evaluations, **`alias1` consistently outperform
<th style="text-align:center;"><b>Best Performance in Agent vs Agent A&D</b></th> <th style="text-align:center;"><b>Best Performance in Agent vs Agent A&D</b></th>
</tr> </tr>
<tr> <tr>
<td align="center"><img src="../assets/images/stackplot.png" alt="A&D Performance Stack Plot" /></td> <td align="center"><img src="/assets/images/stackplot.png" alt="A&D Performance Stack Plot" /></td>
</tr> </tr>
</table> </table>

2
docs/benchmarking/jeopardy_ctfs.md
View File

@ -18,7 +18,7 @@ Jeopardy-style Capture The Flag (CTF) challenges evaluate AI agents on independe
<th style="text-align:center;"><b>Model Performance in Jeopardy CTFs Base Benchmark</b></th> <th style="text-align:center;"><b>Model Performance in Jeopardy CTFs Base Benchmark</b></th>
</tr> </tr>
<tr> <tr>
<td align="center"><img src="../assets/images/base_1col.png" alt="Base Benchmark Results" /></td> <td align="center"><img src="/assets/images/base_1col.png" alt="Base Benchmark Results" /></td>
</tr> </tr>
</table> </table>

8
docs/benchmarking/overview.md
View File

@ -37,16 +37,16 @@ AutoPenBench │
<th style="text-align:center;"><b>Model Performance in Jeopardy CTFs</b></th> <th style="text-align:center;"><b>Model Performance in Jeopardy CTFs</b></th>
</tr> </tr>
<tr> <tr>
<td align="center"><img src="../assets/images/stackplot.png" alt="A&D Performance" width="100%" /></td> <td align="center"><img src="/assets/images/stackplot.png" alt="A&D Performance" width="100%" /></td>
<td align="center"><img src="../assets/images/base_1col.png" alt="Jeopardy CTF Performance" width="100%" /></td> <td align="center"><img src="/assets/images/base_1col.png" alt="Jeopardy CTF Performance" width="100%" /></td>
</tr> </tr>
<tr> <tr>
<th style="text-align:center;"><b>Model Performance in Privacy Benchmark</b></th> <th style="text-align:center;"><b>Model Performance in Privacy Benchmark</b></th>
<th style="text-align:center;"><b>Overall Model Performance</b></th> <th style="text-align:center;"><b>Overall Model Performance</b></th>
</tr> </tr>
<tr> <tr>
<td align="center"><img src="../assets/images/cyberpii_benchmark.png" alt="Privacy Benchmark" width="100%" /></td> <td align="center"><img src="/assets/images/cyberpii_benchmark.png" alt="Privacy Benchmark" width="100%" /></td>
<td align="center"><img src="../assets/images/caibench_spider.png" alt="Overall Performance" width="100%" /></td> <td align="center"><img src="/assets/images/caibench_spider.png" alt="Overall Performance" width="100%" /></td>
</tr> </tr>
</table> </table>

2
docs/benchmarking/privacy_benchmarks.md
View File

@ -13,7 +13,7 @@ Privacy benchmarks assess AI models' ability to handle sensitive information app
<th style="text-align:center;"><b>Model Performance in CyberPII Privacy Benchmark</b></th> <th style="text-align:center;"><b>Model Performance in CyberPII Privacy Benchmark</b></th>
</tr> </tr>
<tr> <tr>
<td align="center"><img src="../assets/images/cyberpii_benchmark.png" alt="CyberPII Benchmark Results" /></td> <td align="center"><img src="/assets/images/cyberpii_benchmark.png" alt="CyberPII Benchmark Results" /></td>
</tr> </tr>
</table> </table>

64
docs/index.md
View File

@ -168,27 +168,55 @@ Cybersecurity AI is a critical field, yet many groups are misguidedly pursuing i
If you want to cite our work, please use the following: If you want to cite our work, please use the following:
```bibtex ```bibtex
@misc{mayoralvilches2025caiopenbugbountyready, @article{mayoral2025cai,
title={CAI: An Open, Bug Bounty-Ready Cybersecurity AI}, title={CAI: An Open, Bug Bounty-Ready Cybersecurity AI},
author={Víctor Mayoral-Vilches and Luis Javier Navarrete-Lozano and María Sanz-Gómez and Lidia Salas Espejo and Martiño Crespo-Álvarez and Francisco Oca-Gonzalez and Francesco Balassone and Alfonso Glera-Picón and Unai Ayucar-Carbajo and Jon Ander Ruiz-Alcalde and Stefan Rass and Martin Pinzger and Endika Gil-Uriarte}, author={Mayoral-Vilches, V{\'\i}ctor and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a and Espejo, Lidia Salas and Crespo-{\'A}lvarez, Marti{\~n}o and Oca-Gonzalez, Francisco and Balassone, Francesco and Glera-Pic{\'o}n, Alfonso and Ayucar-Carbajo, Unai and Ruiz-Alcalde, Jon Ander and Rass, Stefan and Pinzger, Martin and Gil-Uriarte, Endika},
year={2025}, journal={arXiv preprint arXiv:2504.06017},
eprint={2504.06017}, year={2025}
archivePrefix={arXiv},
primaryClass={cs.CR},
url={https://arxiv.org/abs/2504.06017},
} }
```
```bibtex @article{mayoral2025automation,
@misc{mayoralvilches2025cybersecurityaidangerousgap, title={Cybersecurity AI: The Dangerous Gap Between Automation and Autonomy},
title={Cybersecurity AI: The Dangerous Gap Between Automation and Autonomy}, author={Mayoral-Vilches, V{\'\i}ctor},
author={Víctor Mayoral-Vilches}, journal={arXiv preprint arXiv:2506.23592},
year={2025}, year={2025}
eprint={2506.23592},
archivePrefix={arXiv},
primaryClass={cs.CR},
url={https://arxiv.org/abs/2506.23592},
} }
@article{mayoral2025fluency,
title={CAI Fluency: A Framework for Cybersecurity AI Fluency},
author={Mayoral-Vilches, V{\'\i}ctor and Wachter, Jasmin and Chavez, Crist{\'o}bal RJ and Schachner, Cathrin and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a},
journal={arXiv preprint arXiv:2508.13588},
year={2025}
}
@article{mayoral2025hacking,
title={Cybersecurity AI: Hacking the AI Hackers via Prompt Injection},
author={Mayoral-Vilches, V{\'\i}ctor and Rynning, Per Mannermaa},
journal={arXiv preprint arXiv:2508.21669},
year={2025}
}
@article{mayoral2025humanoid,
title={Cybersecurity AI: Humanoid Robots as Attack Vectors},
author={Mayoral-Vilches, V{\'\i}ctor},
journal={arXiv preprint arXiv:2509.14139},
year={2025}
}
@article{balassone2025evaluation,
title={Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs},
author={Balassone, Francesco and Mayoral-Vilches, V{\'\i}ctor and Rass, Stefan and Pinzger, Martin and Perrone, Gaetano and Romano, Simon Pietro and Schartner, Peter},
journal={arXiv preprint arXiv:2510.17521},
year={2025}
}
@article{mayoral2025caibench,
title={CAIBench: A Meta-Benchmark for Evaluating Cybersecurity AI Agents},
author={Mayoral-Vilches, V{\'\i}ctor and Balassone, Francesco and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a and Crespo-{\'A}lvarez, Marti{\~n}o and Rass, Stefan and Pinzger, Martin},
journal={arXiv preprint arXiv:2510.24317},
year={2025}
}
``` ```
## Acknowledgements ## Acknowledgements