Steve Wilson and Gavin Klondike -- OWASP Top Ten for LLM Release

The Application Security Podcast

Steve Wilson and Gavin Klondike are part of the core team for the OWASP Top 10 for Large Language Model Applications project. They join Robert and Chris to discuss the implementation and potential challenges of AI, and present the OWASP Top Ten for LLM version 1.0. Steve and Gavin provide insights into the issues of prompt injection, insecure output handling, training data poisoning, and others. Specifically, they emphasize the significance of understanding the risk of allowing excessive agency to LLMs and the role of secure plugin designs in mitigating vulnerabilities.
The conversation dives deep into the importance of secure supply chains in AI development, looking at the potential risks associated with downloading anonymous models from community-sharing platforms like Huggingface. The discussion also highlights the potential threat implications of hallucinations, where AI produces results based on what it thinks it's expected to produce and tends to please people, rather than generating factually accurate results.
Wilson and Klondike also discuss how certain standard programming principles, such as 'least privilege', can be applied to AI development. They encourage developers to conscientiously manage the extent of privileges they give to their models to avert discrepancies and miscommunications from excessive agency. They conclude the discussion with a forward-looking perspective on how the OWASP Top Ten for LLM Applications will develop in the future.
Links:
OWASP Top Ten for LLM Applications project homepage:
https://owasp.org/www-project-top-10-for-large-language-model-applications/
OWASP Top Ten for LLM Applications summary PDF:
https://owasp.org/www-project-top-10-for-large-language-model-applications/assets/PDF/OWASP-Top-10-for-LLMs-2023-slides-v1_1.pdf
FOLLOW OUR SOCIAL MEDIA:

➜Twitter: @AppSecPodcast
➜LinkedIn: The Application Security Podcast
➜YouTube: https://www.youtube.com/@ApplicationSecurityPodcast

Thanks for Listening!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

فصل ها

1. Introduction (00:00:00)

2. A Threat Model for LLMs (00:01:37)

3. 1 - Prompt Injection (00:05:39)

4. 2 - Insecure Output Handling (00:09:00)

5. 3 - Training Data Poisoning (00:11:35)

6. 4 - Denial of Service (00:15:14)

7. 5 - Suply Chain Vulnerabilities (00:19:11)

8. 6 - Sensitive Information Disclosure (00:28:16)

9. 7 - Insecure Plugin Design (00:33:28)

10. 8 - Excessive Agency (00:38:27)

11. 9 - Overreliance (00:42:39)

12. 10 - Model Theft (00:46:31)

13. The Next Release (00:49:56)