|
19 | 19 | ## Our Content
|
20 | 20 |
|
21 | 21 | [AI Security Overview](docs/ai_security_overview/)
|
| 22 | + [About the AI Exchange](https://owaspai.org/goto/about/) |
22 | 23 | [Summary](https://owaspai.org/goto/summary/)
|
23 |
| - [About the Exchange](https://owaspai.org/goto/about/) |
| 24 | + [How to use this document](https://owaspai.org/goto/document/) |
24 | 25 | [Threats](https://owaspai.org/goto/threatsoverview/)
|
25 | 26 | [Highlight: Threat matrix](https://owaspai.org/goto/aisecuritymatrix/)
|
26 | 27 | [Controls](https://owaspai.org/goto/controlsoverview/)
|
|
37 | 38 | [4. Runtime application security threats and controls](4_runtime_application_security_threats/)
|
38 | 39 | [AI security testing](/docs/5_testing/)
|
39 | 40 | [References](/docs/ai_security_references/)
|
40 |
| - |
41 |
| - |
42 |
| -## Purpose |
43 |
| - |
44 |
| -The OWASP AI Exchange has open sourced the global discussion on the security of AI and data-centric systems. It is an open collaborative project to advance the development of AI security standards and regulations, by providing a comprehensive overview of AI threats, vulnerabilities and controls. This content is feeding into standards for the EU AI Act, ISO/IEC 27090 (AI security), the [OWASP ML top 10](https://mltop10.info/), the [OWASP LLM top 10](https://llmtop10.com/), and [OpenCRE](https://opencre.org) - which we want to use to provide the AI Exchange content through the security chatbot [OpenCRE-Chat](https://opencre.org/chatbot). |
45 |
| - |
46 |
| -Data-centric systems can be divided into AI systems and 'big data' systems that don't have an AI model (e.g. data warehousing, BI, reporting, big data) to which many of the threats and controls in the AI Exchange are relevant: data poisoning, data supply chain management, data pipeline security, etc. |
47 |
| - |
48 |
| -Our **mission** is to be the authoritative source for consensus, foster alignment, and drive collaboration among initiatives - NOT to set a standard, but to drive standards. In other words: be among the top bookmarks of professionals involved in AI security. By doing so, we provide a safe, open, and independent place to find and share insights for everyone. See [AI Exchange LinkedIn page](https://www.linkedin.com/company/owasp-ai-exchange/). |
49 |
| - |
50 |
| -The AI Exchange is displayed here at [owaspai.org](https://owaspai.org) and edited using a [GitHub repository](https://github.com/OWASP/www-project-ai-security-and-privacy-guide/tree/main/content/ai_exchange/content) (see the links _Edit on Github_). It is is an **open-source living publication** for the worldwide exchange of AI security expertise, and part of the [OWASP AI security & privacy guide](https://owasp.org/www-project-ai-security-and-privacy-guide/) project. It is structured as one coherent resource consisting of several sections under 'content', each represented by a page on this website. |
51 |
| - |
52 |
| -<p xmlns:cc="http://creativecommons.org/ns#" xmlns:dct="http://purl.org/dc/terms/"><a property="dct:title" rel="cc:attributionURL" href="https://owaspai.org">OWASP AI Exchange</a> by <span property="cc:attributionName">The AI security community</span> is marked with <a href="http://creativecommons.org/publicdomain/zero/1.0?ref=chooser-v1" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC0 1.0</a> meaning you can use any part freely without copyright and without attribution. If possible, it would be nice if the OWASP AI Exchange is credited and/or linked to, for readers to find more information.</p> |
53 |
| - |
54 |
| -## OWASP AI Initiatives |
55 |
| - |
56 |
| -{{< cards >}} |
57 |
| - {{< small-card link="https://owaspai.org/" title="OWASP AI Exchange (this)" icon="lock-closed" >}} |
58 |
| - {{< small-card link="https://owasp.org/www-project-ai-security-and-privacy-guide/" title="AI security & privacy guide" icon="lock-closed" >}} |
59 |
| - {{< small-card link="https://llmtop10.com/" title="LLM Top 10" icon="brain" >}} |
60 |
| - {{< small-card link="https://mltop10.info/" title="ML Top 10" icon="machinelearning" >}} |
61 |
| -{{< /cards >}} |
0 commit comments