Artwork

Indhold leveret af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.
Player FM - Podcast-app
Gå offline med appen Player FM !

Javan Rasokat and Andra Lezza -- When Chatbots Go Rogue - Lessons Learned from Building and Defending LLM Applications

47:31
 
Del
 

Manage episode 472043747 series 2892775
Indhold leveret af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.

Andra Lezza and Javan Rasokat discuss the complexities of securing AI and LLM applications. With years of experience in Application Security (AppSec), Andra and Javan share their journey and lessons from their DEF CON talk on building and defending LLMs. They explore critical vulnerabilities, prompt injection, hallucinations, and the importance of data security. This discussion sheds light on the evolving landscape of AI and LLM security, offering practical advice for developers and security professionals alike.

Javan’s blog article: Adversarial Misuse of Generative AI

Javan’s recommendation for the TLDR newsletter

Andra's book recommendation: The Cuckoo’s Egg by Cliff Stoll

FOLLOW OUR SOCIAL MEDIA:

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

Thanks for Listening!

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

  continue reading

296 episoder

Artwork
iconDel
 
Manage episode 472043747 series 2892775
Indhold leveret af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af Chris Romeo and Robert Hurlbut, Chris Romeo, and Robert Hurlbut eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.

Andra Lezza and Javan Rasokat discuss the complexities of securing AI and LLM applications. With years of experience in Application Security (AppSec), Andra and Javan share their journey and lessons from their DEF CON talk on building and defending LLMs. They explore critical vulnerabilities, prompt injection, hallucinations, and the importance of data security. This discussion sheds light on the evolving landscape of AI and LLM security, offering practical advice for developers and security professionals alike.

Javan’s blog article: Adversarial Misuse of Generative AI

Javan’s recommendation for the TLDR newsletter

Andra's book recommendation: The Cuckoo’s Egg by Cliff Stoll

FOLLOW OUR SOCIAL MEDIA:

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

Thanks for Listening!

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

  continue reading

296 episoder

Alle episoder

×
 
Loading …

Velkommen til Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Hurtig referencevejledning

Lyt til dette show, mens du udforsker
Afspil