In this episode, Steve Wilson (Project Leader, OWASP Foundation) and Andreas Welsch discuss securing your Large Language Model against common vulnerabilities. Steve shares his findings from co-authoring the OWASP Top 10 on LLMs report and provides valuable advice for listeners looking to improve the security of their Generative AI enabled applications.
Key topics:
- What are the most important vulnerabilities of LLMs?
- What are developers underestimating about these security risks?
- How will these vulnerabilities be exploited?
- How can AI leaders and developers mitigate or prevent it?
Listen to the full episode and hear how you can:
- Balance innovation and security risks of new technologies like generative AI
- Understand the difference between direct and indirect prompt injections
- Prevent over-assigning agency to LLMs
- Establish trust boundaries and treat LLM-generated output as untrusted
Watch this episode on YouTube:
https://youtu.be/TpIowNnAcj4
***********
Disclaimer: Views are the participants’ own and do not represent those of any participant’s past, present, or future employers. Participation in this event is independent of any potential business relationship (past, present, or future) between the participants or between their employers.
More details:
https://www.intelligence-briefing.com
All episodes:
https://www.intelligence-briefing.com/podcast
Get a weekly thought-provoking post in your inbox:
https://www.intelligence-briefing.com/newsletter
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations.
The Nikki Glaser Podcast
Every week comedian and infamous roaster Nikki Glaser provides a fun, fast-paced, and brutally honest look into current pop-culture and her own personal life.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.